How to Outsource Analytics

In this series, I have been emphasizing the importance of statistical modeling in almost every article. While there are plenty of benefits of using statistical models in a more traditional sense (refer to “Why Model?”), in the days when “too much” data is the main challenge, I would dare to say that the most important function of statistical models is that they summarize complex data into simple-to-use “scores.”

In this series, I have been emphasizing the importance of statistical modeling in almost every article. While there are plenty of benefits of using statistical models in a more traditional sense (refer to “Why Model?”), in the days when “too much” data is the main challenge, I would dare to say that the most important function of statistical models is that they summarize complex data into simple-to-use “scores.”

The next important feature would be that models fill in the gaps, transforming “unknowns” to “potentials.” You see, even in the age of ubiquitous data, no one will ever know everything about everybody. For instance, out of 100,000 people you have permission to contact, only a fraction will be “known” wine enthusiasts. With modeling, we can assign scores for “likelihood of being a wine enthusiast” to everyone in the base. Sure, models are not 100 percent accurate, but I’ll take “70 percent chance of afternoon shower” over not knowing the weather forecast for the day of the company picnic.

I’ve already explained other benefits of modeling in detail earlier in this series, but if I may cut it really short, models will help marketers:

1. In deciding whom to engage, as they cannot afford to spam the world and annoy everyone who can read, and

2. In determining what to offer once they decide to engage someone, as consumers are savvier than ever and they will ignore and discard any irrelevant message, no matter how good it may look.

OK, then. I hope you are sold on this idea by now. The next question is, who is going to do all that mathematical work? In a country where jocks rule over geeks, it is clear to me that many folks are more afraid of mathematics than public speaking; which, in its own right, ranks higher than death in terms of the fear factor for many people. If I may paraphrase “Seinfeld,” many folks are figuratively more afraid of giving a eulogy than being in the coffin at a funeral. And thanks to a sub-par math education in the U.S. (and I am not joking about this, having graduated high school on foreign soil), yes, the fear of math tops them all. Scary, heh?

But that’s OK. This is a big world, and there are plenty of people who are really good at mathematics and statistics. That is why I purposefully never got into the mechanics of modeling techniques and related programming issues in this series. Instead, I have been emphasizing how to formulate questions, how to express business goals in a more logical fashion and where to invest to create analytics-ready environments. Then the next question is, “How will you find the right math geeks who can make all your dreams come true?”

If you have a plan to create an internal analytics team, there are a few things to consider before committing to that idea. Too many organizations just hire one or two statisticians, dump all the raw data onto them, and hope to God that they will figure some ways to make money with data, somehow. Good luck with that idea, as:

1. I’ve seen so many failed attempts like that (actually, I’d be shocked if it actually worked), and

2. I am sure God doesn’t micromanage statistical units.

(Similarly, I am almost certain that she doesn’t care much for football or baseball scores of certain teams, either. You don’t think God cares more for the Red Sox than the Yankees, do ya?)

The first challenge is locating good candidates. If you post any online ad for “Statistical Analysts,” you will receive a few hundred resumes per day. But the hiring process is not that simple, as you should ask the right questions to figure out who is a real deal, and who is a poser (and there are many posers out there). Even among qualified candidates with ample statistical knowledge, there are differences between the “Doers” and “Vendor Managers.” Depending on your organizational goal, you must differentiate the two.

Then the next challenge is keeping the team intact. In general, mathematicians and statisticians are not solely motivated by money; they also want constant challenges. Like any smart and creative folks, they will simply pack up and leave, if “they” determine that the job is boring. Just a couple of modeling projects a year with some rudimentary sets of data? Meh. Boring! Promises of upward mobility only work for a fraction of them, as the majority would rather deal with numbers and figures, showing no interest in managing other human beings. So, coming up with interesting and challenging projects, which will also benefit the whole organization, becomes a job in itself. If there are not enough challenges, smart ones will quit on you first. Then they need constant mentoring, as even the smartest statisticians will not know everything about challenges associated with marketing, target audiences and the business world, in general. (If you stumble into a statistician who is even remotely curious about how her salary is paid for, start with her.)

Further, you would need to invest to set up an analytical environment, as well. That includes software, hardware and other supporting staff. Toolsets are becoming much cheaper, but they are not exactly free yet. In fact, some famous statistical software, such as SAS, could be quite expensive year after year, although there are plenty of alternatives now. And they need an “analytics-ready” data environment, as I emphasized countless times in this series (refer to “Chicken or the Egg? Data or Analytics?” and “Marketing and IT; Cats and Dogs”). Such data preparation work is not for statisticians, and most of them are not even good at cleaning up dirty data, anyway. That means you will need different types of developers/programmers on the analytics team. I pointed out that analytical projects call for a cohesive team, not some super-duper analyst who can do it all (refer to “How to Be a Good Data Scientist”).

By now you would say “Jeez Louise, enough already,” as all this is just too much to manage to build just a few models. Suddenly, outsourcing may sound like a great idea. Then you would realize there are many things to consider when outsourcing analytical work.

First, where would you go? Everyone in the data industry and their cousins claim that they can take care of analytics. But in reality, it is a scary place where many who have “analytics” in their taglines do not even touch “predictive analytics.”

Analytics is a word that is abused as much as “Big Data,” so we really need to differentiate them. “Analytics” may mean:

  • Business Intelligence (BI) Reporting: This is mostly about the present, such as the display of key success metrics and dashboard reporting. While it is very important to know about the current state of business, much of so-called “analytics” unfortunately stops right here. Yes, it is good to have a dashboard in your car now, but do you know where you should be going?
  • Descriptive Analytics: This is about how the targets “look.” Common techniques such as profiling, segmentation and clustering fall under this category. These techniques are mainly for describing the target audience to enhance and optimize messages to them. But using these segments as a selection mechanism is not recommended, while many dare to do exactly that (more on this subject in future articles).
  • Predictive Modeling: This is about answering the questions about the future. Who would be more likely to behave certain ways? What communication channels will be most effective for whom? How much is the potential spending level of a prospect? Who is more likely to be a loyal and profitable customer? What are their preferences? Response models, various of types of cloning models, value models, and revenue models, attrition models, etc. all fall under this category, and they require hardcore statistical skills. Plus, as I emphasized earlier, these model scores compact large amounts of complex data into nice bite-size packages.
  • Optimization: This is mostly about budget allocation and attribution. Marketing agencies (or media buyers) generally deal with channel optimization and spending analysis, at times using econometrics models. This type of statistical work calls for different types of expertise, but many still insist on calling it simply “analytics.”

Let’s say that for the purpose of customer-level targeting and personalization, we decided to outsource the “predictive” modeling projects. What are our options?

We may consider:

  • Individual Consultants: In-house consultants are dedicated to your business for the duration of the contract, guaranteeing full access like an employee. But they are there for you only temporarily, with one foot out the door all the time. And when they do leave, all the knowledge walks away with them. Depending on the rate, the costs can add up.
  • Standalone Analytical Service Providers: Analytical work is all they do, so you get focused professionals with broad technical and institutional knowledge. Many of them are entrepreneurs, but that may work against you, as they could often be understaffed and stretched thin. They also tend to charge for every little step, with not many freebies. They are generally open to use any type of data, but the majority of them do not have secure sources of third-party data, which could be essential for certain types of analytics involving prospecting.
  • Database Service Providers: Almost all data compilers and brokers have statistical units, as they need to fill in the gap within their data assets with statistical techniques. (You didn’t think that they knew everyone’s income or age, did you?) For that reason, they have deep knowledge in all types of data, as well as in many industry verticals. They provide a one-stop shop environment with deep resource pools and a variety of data processing capabilities. However, they may not be as agile as smaller analytical shops, and analytics units may be tucked away somewhere within large and complex organizations. They also tend to emphasize the use of their own data, as after all, their main cash cows are their data assets.
  • Direct Marketing Agencies: Agencies are very strategic, as they touch all aspects of marketing and control creative processes through segmentation. Many large agencies boast full-scale analytical units, capable of all types of analytics that I explained earlier. But some agencies have very small teams, stretched really thin—just barely handling the reporting aspect, not any advanced analytics. Some just admit that predictive analytics is not part of their core competencies, and they may outsource such projects (not that it is a bad thing).

As you can see here, there is no clear-cut answer to “with whom you should you work.” Basically, you will need to check out all types of analysts and service providers to determine the partner best suitable for your long- and short-term business purposes, not just analytical goals. Often, many marketers just go with the lowest bidder. But pricing is just one of many elements to be considered. Here, allow me to introduce “10 Essential Items to Consider When Outsourcing Analytics.”

1. Consulting Capabilities: I put this on the top of the list, as being a translator between the marketing and the technology world is the most important differentiator (refer to “How to Be a Good Data Scientist”). They must understand the business goals and marketing needs, prescribe suitable solutions, convert such goals into mathematical expressions and define targets, making the best of available data. If they lack strategic vision to set up the data roadmap, statistical knowledge alone will not be enough to achieve the goals. And such business goals vary greatly depending on the industry, channel usage and related success metrics. Good consultants always ask questions first, while sub-par ones will try to force-fit marketers’ goals into their toolsets and methodologies.

Translating marketing goals into specific courses of action is a skill in itself. A good analytical partner should be capable of building a data roadmap (not just statistical steps) with a deep understanding of the business impact of resultant models. They should be able to break down larger goals into smaller steps, creating proper phased approaches. The plan may call for multiple models, all kinds of pre- and post-selection rules, or even external data acquisition, while remaining sensitive to overall costs.

The target definition is the core of all these considerations, which requires years of experience and industry knowledge. Simply, the wrong or inadequate targeting decision leads to disastrous results, no matter how sound the mathematical work is (refer to “Art of Targeting”).

Another important quality of a good analytical partner is the ability to create usefulness out of seemingly chaotic and unstructured data environments. Modeling is not about waiting for the perfect set of data, but about making the best of available data. In many modeling bake-offs, the winners are often decided by the creative usage of provided data, not just statistical techniques.

Finally, the consultative approach is important, as models do not exist in a vacuum, but they have to fit into the marketing engine. Be aware of the ones who want to change the world around their precious algorithms, as they are geeks not strategists. And the ones who understand the entire marketing cycle will give advice on what the next phase should be, as marketing efforts must be perpetual, not transient.

So, how will you find consultants? Ask the following questions:

  • Are they “listening” to you?
  • Can they repeat “your” goals in their own words?
  • Do their roadmaps cover both short- and long-term goals?
  • Are they confident enough to correct you?
  • Do they understand “non-statistical” elements in marketing?
  • Have they “been there, done that” for real, or just in theories?

2. Data Processing Capabilities: I know that some people look down upon the word “processing.” But data manipulation is the most important key step “before” any type of advanced analytics even begins. Simply, “garbage-in, garbage out.” And unfortunately, most datasets are completely unsuitable for analytics and modeling. In general, easily more than 80 percent of model development time goes into “fixing” the data, as most are unstructured and unrefined. I have been repeatedly emphasizing the importance of a “model-ready” (or “analytics-ready”) environment for that reason.

However, the reality dictates that the majority of databases are indeed NOT model-ready, and most of them are not even close to it. Well, someone has to clean up the mess. And in this data business, the last one who touches the dataset becomes responsible for all the errors and mistakes made to it thus far. I know it is not fair, but that is why we need to look at the potential partner’s ability to handle large and really messy data, not just the statistical savviness displayed in glossy presentations.

Yes, that dirty work includes data conversion, edit/hygiene, categorization/tagging, data summarization and variable creation, encompassing all kinds of numeric, character and freeform data (refer to “Beyond RFM Data” and “Freeform Data Aren’t Exactly Free”). It is not the most glorious part of this business, but data consistency is the key to successful implementation of any advanced analytics. So, if a model-ready environment is not available, someone had better know how to make the best of whatever is given. I have seen too many meltdowns in “before” and “after” modeling steps due to inconsistencies in databases.

So, grill the candidates with the following questions:

  • If they support file conversions, edit, categorization and summarization
  • How big of a dataset is too big, and how many files/tables are too many for them
  • How much free-form data are too much for them
  • Ask for sample model variables that they have created in the past

3. Track Records in the Industry: It can be argued that industry knowledge is even more crucial for the success than statistical know-how, as nuances are often “Lost in Translation” without relevant industry experience. In fact, some may not even be able to carry on a proper conversation with a client without it, leading to all kinds of wrong assumptions. I have seen a case where “real” rocket scientists messed up models for credit card campaigns.

The No. 1 reason why industry experience is important is everyone’s success metrics are unique. Just to name a few, financial services (banking, credit card, insurance, investment, etc.), travel and hospitality, entertainment, packaged goods, online and offline retail, catalogs, publication, telecommunications/utilities, non-profit and political organizations all call for different types of analytics and models, as their business models and the way they interact with target audiences are vastly different. For example, building a model (or a database, for that matter) for businesses where they hand over merchandise “before” they collect money is fundamentally different than the ones where exchange happens simultaneously. Even a simple concept of payment date or transaction date cannot be treated the same way. For retailers, recent dates could be better for business, but for subscription business, older dates may carry more weight. And these are just some examples with “dates,” before touching any dollar figures or other fun stuff.

Then the job gets even more complicated, if we further divide all of these industries by B-to-B vs. B-to-C, where available data do not even look similar. On top of that, divisional ROI metrics may be completely different, and even terminology and culture may play a role in all of this. When you are a consultant, you really don’t want to stop the flow of a meeting to clarify some unfamiliar acronyms, as you are supposed to know them all.

So, always demand specific industry references and examine client roasters, if allowed. (Many clients specifically ask vendors not to use their names as references.) Basically, watch out for the ones who push one-size-fits-all cookie-cutter solutions. You deserve way more than that.

4. Types of Models Supported: Speaking of cookie-cutter stuff, we need to be concerned with types of models that the outsourcing partner would support. Sure, nobody employs every technique, and no one can be good at everything. But we need to watch out for the “One-trick Ponies.”

This could be a tricky issue, as we are going into a more technical domain. Plus, marketers should not self-prescribe with specific techniques, instead of clearly stating their business goals (refer to “Marketing and IT; Cats and Dogs”). Some of the modeling goals are:

  • Rank and select prospect names
  • Lead scoring
  • Cross-sell/upsell
  • Segment the universe for messaging strategy
  • Pinpoint the attrition point
  • Assign lifetime values for prospects and customers
  • Optimize media/channel spending
  • Create new product packages
  • Detect fraud
  • Etc.

Unless you have successfully dealt with the outsourcing partner in the past (or you have a degree in statistics), do not blurt out words like Neural-net, CHAID, Cluster Analysis, Multiple Regression, Discriminant Function Analysis, etc. That would be like demanding specific medication before your new doctor even asks about your symptoms. The key is meeting your business goals, not fulfilling buzzwords. Let them present their methodology “after” the goal discussion. Nevertheless, see if the potential partner is pushing one or two specific techniques or solutions all the time.

5. Speed of Execution: In modern marketing, speed to action is the king. Speed wins, and speed gains respect. However, when it comes to modeling or other advanced analytics, you may be shocked by the wide range of time estimates provided by each outsourcing vendor. To be fair they are covering themselves, mainly because they have no idea what kind of messy data they will receive. As I mentioned earlier, pre-model data preparation and manipulation are critical components, and they are the most time-consuming part of all; especially when available data are in bad shape. Post-model scoring, audit and usage support may elongate the timeline. The key is to differentiate such pre- and post-modeling processes in the time estimate.

Even for pure modeling elements, time estimates vary greatly, depending on the complexity of assignments. Surely, a simple cloning model with basic demographic data would be much easier to execute than the ones that involve ample amounts of transaction- and event-level data, coming from all types of channels. If time-series elements are added, it will definitely be more complex. Typical clustering work is known to take longer than regression models with clear target definitions. If multiple models are required for the project, it will obviously take more time to finish the whole job.

Now, the interesting thing about building a model is that analysts don’t really finish it, but they just run out of time—much like the way marketers work on PowerPoint presentations. The commonality is that we can basically tweak models or decks forever, but we have to stop at some point.

However, with all kinds of automated tools and macros, model development time has decreased dramatically in past decades. We really came a long way since the first application of statistical techniques to marketing, and no one should be quoting a 1980s timeline in this century. But some still do. I know vendors are trained to follow the guideline “always under-promise and over-deliver,” but still.

An interesting aspect of this dilemma is that we can negotiate the timeline by asking for simpler and less sophisticated versions with diminished accuracy. If, hypothetically, it takes a week to be 98 percent accurate, but it only takes a day to be 90 percent accurate, what would you pick? That should be the business decision.

So, what is a general guideline? Again, it really depends on many factors, but allow me to share a version of it:

  • Pre-modeling Processing

– Data Conversions: from half a day to weeks

– Data Append/Enhancement: between overnight and two days

– Data Edit and Summarization: Data-dependent

  • Modeling: Ranges from half a day to weeks

– Depends on type, number of models and complexity

  • Scoring: from half a day to one week

– Mainly depends on number of records and state of the database to be scored

I know these are wide ranges, but watch out for the ones that routinely quote 30 days or more for simple clone models. They may not know what they are doing, or worse, they may be some mathematical perfectionists who don’t understand the marketing needs.

6. Pricing Structure: Some marketers would put this on top of the checklist, or worse, use the pricing factor as the only criterion. Obviously, I disagree. (Full disclosure: I have been on the service side of the fence during my entire career.) Yes, every project must make an economic sense in the end, but the budget should not and cannot be the sole deciding factor in choosing an outsourcing partner. There are many specialists under famous brand names who command top dollars, and then there are many data vendors who throw in “free” models, disrupting the ecosystem. Either way, one should not jump to conclusions too fast, as there is no free lunch, after all. In any case, I strongly recommend that no one should start the meeting with pricing questions (hence, this article). When you get to the pricing part, ask what the price includes, as the analytical journey could be a series of long and winding roads. Some of the biggest factors that need to be considered are:

  • Multiple Model Discounts—Less for second or third models within a project?
  • Pre-developed (off-the-shelf) Models—These can be “much” cheaper than custom models, while not custom-fitted.
  • Acquisition vs. CRM—Employing client-specific variables certainly increases the cost.
  • Regression Models vs. Other Types—At times, types of techniques may affect the price.
  • Clustering and Segmentations—They are generally priced much higher than target-specific models.

Again, it really depends on the complexity factor more than anything else, and the pre- and post-modeling process must be estimated and priced separately. Non-modeling charges often add up fast, and you should ask for unit prices and minimum charges for each step.

Scoring charges in time can be expensive, too, so negotiate for discounts for routine scoring of the same models. Some may offer all-inclusive package pricing for everything. The important thing is that you must be consistent with the checklist when shopping around with multiple candidates.

7. Documentation: When you pay for a custom model (not pre-developed, off-the-shelf ones), you get to own the algorithm. Because algorithms are not tangible items, the knowledge is to be transformed in model documents. Beware of the ones who offer “black-box” solutions with comments like, “Oh, it will work, so trust us.”

Good model documents must include the following, at the minimum:

  • Target and Comparison Universe Definitions: What was the target variable (or “dependent” variable) and how was it defined? How was the comparison universe defined? Was there any “pre-selection” for either of the universes? These are the most important factors in any model—even more than the mechanics of the model itself.
  • List of Variables: What are the “independent” variables? How were they transformed or binned? From where did they originate? Often, these model variables describe the nature of the model, and they should make intuitive sense.
  • Model Algorithms: What is the actual algorithm? What are the assigned weight for each independent variable?
  • Gains Chart: We need to examine potential effectiveness of the model. What are the “gains” for each model group, from top to bottom (e.g., 320 percent gain at the top model group in comparison to the whole universe)? How fast do such gains decrease as we move down the scale? How do the gains factors compare against the validation sample? A graphic representation would be nice, too.

For custom models, it is customary to have a formal model presentation, full documentation and scoring script in designated programming languages. In addition, if client files are provided, ask for a waterfall report that details input and output counts of each step. After the model scoring, it is also customary for the vendor to provide a scored universe count by model group. You will be shocked to find out that many so-called analytical vendors do not provide thorough documentation. Therefore, it is recommended to ask for sample documents upfront.

8. Scoring Validation: Models are built and presented properly, but the job is not done until the models are applied to the universe from which the names are ranked and selected for campaigns. I have seen too many major meltdowns at this stage. Simply, it is one thing to develop models with a few hundred thousand record samples, but it is quite another to apply the algorithm to millions of records. I am not saying that the scoring job always falls onto the developers, as you may have an internal team or a separate vendor for such ongoing processes. But do not let the model developer completely leave the building until everything checks out.

The model should have been validated against the validation sample by then, but live scoring may reveal all kinds of inconsistencies. You may also want to back-test the algorithms with past campaign results, as well. In short, many things go wrong “after” the modeling steps. When I hear customers complaining about models, I often find that the modeling is the only part that was done properly, and “before” and “after” steps were all messed up. Further, even machines misunderstand each other, as any differences in platform or scripting language may cause discrepancies. Or, maybe there was no technical error, but missing values may have caused inconsistencies (refer to “Missing Data Can Be Meaningful”). Nonetheless, the model developers would have the best insight as to what could have gone wrong, so make sure that they are available for questions after models are presented and delivered.

9. Back-end Analysis: Good analytics is all about applying learnings from past campaigns—good or bad—to new iterations of efforts. We often call it “closed-loop marketing—while many marketers often neglect to follow up. Any respectful analytics shop must be aware of it, while they may classify such work separately from modeling or other analytical projects. At the minimum, you need to check out if they even offer such services. In fact, so-called “match-back analysis” is not as simple as just matching campaign files against responders in this omnichannel environment. When many channels are employed at the same time, allocation of credit (i.e., “what worked?”) may call for all kinds of business rules or even dedicated models.

While you are at it, ask for a cheaper version of “canned” reports, as well, as custom back-end analysis can be even more costly than the modeling job itself, over time. Pre-developed reports may not include all the ROI metrics that you’re looking for (e.g., open, clickthrough, conversion rates, plus revenue and orders-per-mailed, per order, per display, per email, per conversion. etc.). So ask for sample reports upfront.

If you start breaking down all these figures by data source, campaign, time series, model group, offer, creative, targeting criteria, channel, ad server, publisher, keywords, etc., it can be unwieldy really fast. So contain yourself, as no one can understand 100-page reports, anyway. See if the analysts can guide you with such planning, as well. Lastly, if you are so into ROI analysis, get ready to share the “cost” side of the equation with the selected partner. Some jobs are on the marketers.

10. Ongoing Support: Models have a finite shelf life, as all kinds of changes happen in the real world. Seasonality may be a factor, or the business model or strategy may have changed. Fluctuations in data availability and quality further complicate the matter. Basically assumptions like “all things being equal” only happen in textbooks, so marketers must plan for periodic review of models and business rules.

A sure sign of trouble is decreasing effectiveness of models. When in doubt, consult the developers and they may recommend a re-fit or complete re-development of models. Quarterly reviews would be ideal, but if the cost becomes an issue, start with 6-month or yearly reviews, but never go past more than a year without any review. Some vendors may offer discounts for redevelopment, so ask for the price quote upfront.

I know this is a long list of things to check, but picking the right partner is very important, as it often becomes a long-term relationship. And you may find it strange that I didn’t even list “technical capabilities” at all. That is because:

1. Many marketers are not equipped to dig deep into the technical realm anyway, and

2. The difference between the most mathematically sound models and the ones from the opposite end of the spectrum is not nearly as critical as other factors I listed in this article.

In other words, even the worst model in the bake-off would be much better than no model, if these other business criterion are well-considered. So, happy shopping with this list, and I hope you find the right partner. Employing analytics is not an option when living in the sea of data.

Missing Data Can Be Meaningful

No matter how big the Big Data gets, we will never know everything about everything. Well, according to the super-duper computer called “Deep Thought” in the movie “The Hitchhiker’s Guide to the Galaxy” (don’t bother to watch it if you don’t care for the British sense of humour), the answer to “The Ultimate Question of Life, the Universe, and Everything” is “42.” Coincidentally, that is also my favorite number to bet on (I have my reasons), but I highly doubt that even that huge fictitious computer with unlimited access to “everything” provided that numeric answer with conviction after 7½ million years of computing and checking. At best, that “42” is an estimated figure of a sort, based on some fancy algorithm. And in the movie, even Deep Thought pointed out that “the answer is meaningless, because the beings who instructed it never actually knew what the Question was.” Ha! Isn’t that what I have been saying all along? For any type of analytics to be meaningful, one must properly define the question first. And what to do with the answer that comes out of an algorithm is entirely up to us humans, or in the business world, the decision-makers. (Who are probably human.)

No matter how big the Big Data gets, we will never know everything about everything. Well, according to the super-duper computer called “Deep Thought” in the movie “The Hitchhiker’s Guide to the Galaxy” (don’t bother to watch it if you don’t care for the British sense of humour), the answer to “The Ultimate Question of Life, the Universe, and Everything” is “42.” Coincidentally, that is also my favorite number to bet on (I have my reasons), but I highly doubt that even that huge fictitious computer with unlimited access to “everything” provided that numeric answer with conviction after 7½ million years of computing and checking. At best, that “42” is an estimated figure of a sort, based on some fancy algorithm. And in the movie, even Deep Thought pointed out that “the answer is meaningless, because the beings who instructed it never actually knew what the Question was.” Ha! Isn’t that what I have been saying all along? For any type of analytics to be meaningful, one must properly define the question first. And what to do with the answer that comes out of an algorithm is entirely up to us humans, or in the business world, the decision-makers. (Who are probably human.)

Analytics is about making the best of what we know. Good analysts do not wait for a perfect dataset (it will never come by, anyway). And businesspeople have no patience to wait for anything. Big Data is big because we digitize everything, and everything that is digitized is stored somewhere in forms of data. For example, even if we collect mobile device usage data from just pockets of the population with certain brands of mobile services in a particular area, the sheer size of the resultant dataset becomes really big, really fast. And most unstructured databases are designed to collect and store what is known. If you flip that around to see if you know every little behavior through mobile devices for “everyone,” you will be shocked to see how small the size of the population associated with meaningful data really is. Let’s imagine that we can describe human beings with 1,000 variables coming from all sorts of sources, out of 200 million people. How many would have even 10 percent of the 1,000 variables filled with some useful information? Not many, and definitely not 100 percent. Well, we have more data than ever in the history of mankind, but still not for every case for everyone.

In my previous columns, I pointed out that decision-making is about ranking different options, and to rank anything properly. We must employee predictive analytics (refer to “It’s All About Ranking“). And for ranking based on the scores resulting from predictive models to be effective, the datasets must be summarized to the level that is to be ranked (e.g., individuals, households, companies, emails, etc.). That is why transaction or event-level datasets must be transformed to “buyer-centric” portraits before any modeling activity begins. Again, it is not about the transaction or the products, but it is about the buyers, if you are doing all this to do business with people.

Trouble with buyer- or individual-centric databases is that such transformation of data structure creates lots of holes. Even if you have meticulously collected every transaction record that matters (and that will be the day), if someone did not buy a certain item, any variable that is created based on the purchase record of that particular item will have nothing to report for that person. Likewise, if you have a whole series of variables to differentiate online and offline channel behaviors, what would the online portion contain if the consumer in question never bought anything through the Web? Absolutely nothing. But in the business of predictive analytics, what did not happen is as important as what happened. Even a simple concept of “response” is only meaningful when compared to “non-response,” and the difference between the two groups becomes the basis for the “response” model algorithm.

Capturing the Meanings Behind Missing Data
Missing data are all around us. And there are many reasons why they are missing, too. It could be that there is nothing to report, as in aforementioned examples. Or, there could be errors in data collection—and there are lots of those, too. Maybe you don’t have access to certain pockets of data due to corporate, legal, confidentiality or privacy reasons. Or, maybe records did not match properly when you tried to merge disparate datasets or append external data. These things happen all the time. And, in fact, I have never seen any dataset without a missing value since I left school (and that was a long time ago). In school, the professors just made up fictitious datasets to emphasize certain phenomena as examples. In real life, databases have more holes than Swiss cheese. In marketing databases? Forget about it. We all make do with what we know, even in this day and age.

Then, let’s ask a philosophical question here:

  • If missing data are inevitable, what do we do about it?
  • How would we record them in databases?
  • Should we just leave them alone?
  • Or should we try to fill in the gaps?
  • If so, how?

The answer to all this is definitely not 42, but I’ll tell you this: Even missing data have meanings, and not all missing data are created equal, either.

Furthermore, missing data often contain interesting stories behind them. For example, certain demographic variables may be missing only for extremely wealthy people and very poor people, as their residency data are generally not exposed (for different reasons, of course). And that, in itself, is a story. Likewise, some data may be missing in certain geographic areas or for certain age groups. Collection of certain types of data may be illegal in some states. “Not” having any data on online shopping behavior or mobile activity may mean something interesting for your business, if we dig deeper into it without falling into the trap of predicting legal or corporate boundaries, instead of predicting consumer behaviors.

In terms of how to deal with missing data, let’s start with numeric data, such as dollars, days, counters, etc. Some numeric data simply may not be there, if there is no associated transaction to report. Now, if they are about “total dollar spending” and “number of transactions” in a certain category, for example, they can be initiated as zero and remain as zero in cases like this. The counter simply did not start clicking, and it can be reported as zero if nothing happened.

Some numbers are incalculable, though. If you are calculating “Average Amount per Online Transaction,” and if there is no online transaction for a particular customer, that is a situation for mathematical singularity—as we can’t divide anything by zero. In such cases, the average amount should be recorded as: “.”, blank, or any value that represents a pure missing value. But it should never be recorded as zero. And that is the key in dealing with missing numeric information; that zero should be reserved for real zeros, and nothing else.

I have seen too many cases where missing numeric values are filled with zeros, and I must say that such a practice is definitely frowned-upon. If you have to pick just one takeaway from this article, that’s it. Like I emphasized, not all missing values are the same, and zero is not the way you record them. Zeros should never represent lack of information.

Take the example of a popular demographic variable, “Number of Children in the Household.” This is a very predictable variable—not just for purchase behavior of children’s products, but for many other things. Now, it is a simple number, but it should never be treated as a simple variable—as, in this case, lack of information is not the evidence of non-existence. Let’s say that you are purchasing this data from a third-party data compiler (or a data broker). If you don’t see a positive number in that field, it could be because:

  1. The household in question really does not have a child;
  2. Even the data-collector doesn’t have the information; or
  3. The data collector has the information, but the household record did not match to the vendor’s record, for some reason.

If that field contains a number like 1, 2 or 3, that’s easy, as they will represent the number of children in that household. But the zero should be reserved for cases where the data collector has a positive confirmation that the household in question indeed does not have any children. If it is unknown, it should be marked as blank, “.” (Many statistical softwares, such as SAS, record missing values this way.) Or use “U” (though an alpha character should not be in a numeric field).

If it is a case of non-match to the external data source, then there should be a separate indicator for it. The fact that the record did not match to a professional data compiler’s list may mean something. And I’ve seen cases where such non-matching indicators are made to model algorithms along with other valid data, as in the case where missing indicators of income display the same directional tendency as high-income households.

Now, if the data compiler in question boldly inputs zeros for the cases of unknowns? Take a deep breath, fire the vendor, and don’t deal with the company again, as it is a sign that its representatives do not know what they are doing in the data business. I have done so in the past, and you can do it, too. (More on how to shop for external data in future articles.)

For non-numeric categorical data, similar rules apply. Some values could be truly “blank,” and those should be treated separately from “Unknown,” or “Not Available.” As a practice, let’s list all kinds of possible missing values in codes, texts or other character fields:

  • ” “—blank or “null”
  • “N/A,” “Not Available,” or “Not Applicable”
  • “Unknown”
  • “Other”—If it is originating from some type of multiple choice survey or pull-down menu
  • “Not Answered” or “Not Provided”—This indicates that the subjects were asked, but they refused to answer. Very different from “Unknown.”
  • “0”—In this case, the answer can be expressed in numbers. Again, only for known zeros.
  • “Non-match”—Not matched to other internal or external data sources
  • Etc.

It is entirely possible that all these values may be highly correlated to each other and move along the same predictive direction. However, there are many cases where they do not. And if they are combined into just one value, such as zero or blank, we will never be able to detect such nuances. In fact, I’ve seen many cases where one or more of these missing indicators move together with other “known” values in models. Again, missing data have meanings, too.

Filling in the Gaps
Nonetheless, missing data do not have to left as missing, blank or unknown all the time. With statistical modeling techniques, we can fill in the gaps with projected values. You didn’t think that all those data compilers really knew the income level of every household in the country, did you? It is not a big secret that much of those figures are modeled with other available data.

Such inferred statistics are everywhere. Popular variables, such as householder age, home owner/renter indicator, housing value, household income or—in the case of business data—the number of employees and sales volume contain modeled values. And there is nothing wrong with that, in the world where no one really knows everything about everything. If you understand the limitations of modeling techniques, it is quite alright to employ modeled values—which are much better alternatives to highly educated guesses—in decision-making processes. We just need to be a little careful, as models often fail to predict extreme values, such as household incomes over $500,000/year, or specific figures, such as incomes of $87,500. But “ranges” of household income, for example, can be predicted at a high confidence level, though it technically requires many separate algorithms and carefully constructed input variables in various phases. But such technicality is an issue that professional number crunchers should deal with, like in any other predictive businesses. Decision-makers should just be aware of the reality of real and inferred data.

Such imputation practices can be applied to any data source, not just compiled databases by professional data brokers. Statisticians often impute values when they encounter missing values, and there are many different methods of imputation. I haven’t met two statisticians who completely agree with each other when it comes to imputation methodologies, though. That is why it is important for an organization to have a unified rule for each variable regarding its imputation method (or lack thereof). When multiple analysts employ different methods, it often becomes the very source of inconsistent or erroneous results at the application stage. It is always more prudent to have the calculation done upfront, and store the inferred values in a consistent manner in the main database.

In terms of how that is done, there could be a long debate among the mathematical geeks. Will it be a simple average of non-missing values? If such a method is to be employed, what is the minimum required fill-rate of the variable in question? Surely, you do not want to project 95 percent of the population with 5 percent known values? Or will the missing values be replaced with modeled values, as in previous examples? If so, what would be the source of target data? What about potential biases that may exist because of data collection practices and their limitations? What should be the target definition? In what kind of ranges? Or should the target definition remain as a continuous figure? How would you differentiate modeled and real values in the database? Would you embed indicators for inferred values? Or would you forego such flags in the name of speed and convenience for users?

The important matter is not the rules or methodologies, but the consistency of them throughout the organization and the databases. That way, all users and analysts will have the same starting point, no matter what the analytical purposes are. There could be a long debate in terms of what methodology should be employed and deployed. But once the dust settles, all data fields should be treated by pre-determined rules during the database update processes, avoiding costly errors in the downstream. All too often, inconsistent imputation methods lead to inconsistent results.

If, by some chance, individual statisticians end up with freedom to come up with their own ways to fill in the blanks, then the model-scoring code in question must include missing value imputation algorithms without an exception, granted that such practice will elongate the model application processes and significantly increase chances for errors. It is also important that non-statistical users should be educated about the basics of missing data and associated imputation methods, so that everyone who has access to the database shares a common understanding of what they are dealing with. That list includes external data providers and partners, and it is strongly recommended that data dictionaries must include employed imputation rules wherever applicable.

Keep an Eye on the Missing Rate
Often, we get to find out that the missing rate of certain variables is going out of control because models become ineffective and campaigns start to yield disappointing results. Conversely, it can be stated that fluctuations in missing data ratios greatly affect the predictive power of models or any related statistical works. It goes without saying that a consistent influx of fresh data matters more than the construction and the quality of models and algorithms. It is a classic case of a garbage-in-garbage-out scenario, and that is why good data governance practices must include a time-series comparison of the missing rate of every critical variable in the database. If, all of a sudden, an important predictor’s fill-rate drops below a certain point, no analyst in this world can sustain the predictive power of the model algorithm, unless it is rebuilt with a whole new set of variables. The shelf life of models is definitely finite, but nothing deteriorates effectiveness of models faster than inconsistent data. And a fluctuating missing rate is a good indicator of such an inconsistency.

Likewise, if the model score distribution starts to deviate from the original model curve from the development and validation samples, it is prudent to check the missing rate of every variable used in the model. Any sudden changes in model score distribution are a good indicator that something undesirable is going on in the database (more on model quality control in future columns).

These few guidelines regarding the treatment of missing data will add more flavors to statistical models and analytics in general. In turn, proper handling of missing data will prolong the predictive power of models, as well. Missing data have hidden meanings, but they are revealed only when they are treated properly. And we need to do that until the day we get to know everything about everything. Unless you are just happy with that answer of “42.”

Beyond RFM Data

In the world of predictive analytics, the transaction data is the king of the hill. The master of the domain. The protector of the realm. Why? Because they are hands-down the most powerful predictors. If I may borrow the term that my mentor coined for our cooperative venture more than a decade ago (before anyone even uttered the word “Big Data”), “The past behavior is the best predictor of the future behavior.” Indeed. Back then, we had built a platform that nowadays could easily have qualified as Big Data. The platform predicted people’s future behaviors on a massive scale, and it worked really well, so I still stand by that statement.

In the world of predictive analytics, the transaction data is the king of the hill. The master of the domain. The protector of the realm. Why? Because they are hands-down the most powerful predictors. If I may borrow the term that my mentor coined for our cooperative venture more than a decade ago (before anyone even uttered the word “Big Data”), “The past behavior is the best predictor of the future behavior.” Indeed. Back then, we had built a platform that nowadays could easily have qualified as Big Data. The platform predicted people’s future behaviors on a massive scale, and it worked really well, so I still stand by that statement.

How so? At the risk of sounding like a pompous mathematical smartypants (I’m really not), it is because people do not change that much, or if so, not so rapidly. Every move you make is on some predictive curve. What you been buying, clicking, browsing, smelling or coveting somehow leads to the next move. Well, not all the time. (Maybe you just like to “look” at pretty shoes?) But with enough data, we can calculate the probability with some confidence that you would be an outdoors type, or a golfer, or a relaxing type on a cruise ship, or a risk-averse investor, or a wine enthusiast, or into fashion, or a passionate gardener, or a sci-fi geek, or a professional wrestling fan. Beyond affinity scores listed here, we can predict future value of each customer or prospect and possible attrition points, as well. And behind all those predictive models (and I have seen countless algorithms), the leading predictors are mostly transaction data, if you are lucky enough to get your hands on them. In the age of ubiquitous data and at the dawn of the “Internet of Things,” more marketers will be in that lucky group if they are diligent about data collection and refinement. Yes, in the near future, even a refrigerator will be able to order groceries, but don’t forget that only the collection mechanism will be different there. We still have to collect, refine and analyze the transaction data.

Last month, I talked about three major types of data (refer to “Big Data Must Get Smaller“), which are:
1. Descriptive Data
2. Behavioral Data (mostly Transaction Data)
3. Attitudinal Data.

If you gain access to all three elements with decent coverage, you will have tremendous predictive power when it comes to human behaviors. Unfortunately, it is really difficult to accumulate attitudinal data on a large scale with individual-level details (i.e., knowing who’s behind all those sentiments). Behavioral data, mostly in forms of transaction data, are also not easy to collect and maintain (non-transaction behavioral data are even bigger and harder to handle), but I’d say it is definitely worth the effort, as most of what we call Big Data fall under this category. Conversely, one can just purchase descriptive data, which are what we generally call demographic or firmographic data, from data compilers or brokers. The sellers (there are many) will even do the data-append processing for you and they may also throw in a few free profile reports with it.

Now, when we start talking about the transaction data, many marketers will respond “Oh, you mean RFM data?” Well, that is not completely off-base, because “Recency, Frequency and Monetary” data certainly occupy important positions in the family of transaction data. But they hardly are the whole thing, and the term is misused as frequently as “Big Data.” Transaction data are so much more than simple RFM variables.

RFM Data Is Just a Good Start
The term RFM should be used more as a checklist for marketers, not as design guidelines—or limitations in many cases—for data professionals. How recently did this particular customer purchase our product, and how frequently did she do that and how much money did she spend with us? Answering these questions is a good start, but stopping there would seriously limit the potential of transaction data. Further, this line of questioning would lead the interrogation efforts to simple “filtering,” as in: “Select all customers who purchased anything with a price tag over $100 more than once in past 12 months.” Many data users may think that this query is somewhat complex, but it really is just a one-dimensional view of the universe. And unfortunately, no customer is one-dimensional. And this query is just one slice of truth from the marketer’s point of view, not the customer’s. If you want to get really deep, the view must be “buyer-centric,” not product-, channel-, division-, seller- or company-centric. And the database structure should reflect that view (refer to “It’s All About Ranking,” where the concept of “Analytical Sandbox” is introduced).

Transaction data by definition describe the transactions, not the buyers. If you would like to describe a buyer or if you are trying to predict the buyer’s future behavior, you need to convert the transaction data into “descriptors of the buyers” first. What is the difference? It is the same data looked at through a different window—front vs. side window—but the effect is huge.

Even if we think about just one simple transaction with one item, instead of describing the shopping basket as “transaction happened on July 3, 2014, containing the Coldplay’s latest CD ‘Ghost Stories’ priced at $11.88,” a buyer-centric description would read: “A recent CD buyer in Rock genre with an average spending level in the music category under $20.” The trick is to describe the buyer, not the product or the transaction. If that customer has many orders and items in his purchase history (let’s say he downloaded a few songs to his portable devices, as well), the description of the buyer would become much richer. If you collect all of his past purchase history, it gets even more colorful, as in: “A recent music CD or MP3 buyer in rock, classical and jazz genres with 24-month purchase totaling to 13 orders containing 16 items with total spending valued in $100-$150 range and $11 average order size.” Of course you would store all this using many different variables (such as genre indicators, number of orders, number of items, total dollars spent during the past 24 months, average order amount and number of weeks since last purchase in the music category, etc.). But the point is that the story would come out this way when you change the perspective.

Creating a Buyer-Centric Portrait
The whole process of creating a buyer-centric portrait starts with data summarization (or de-normalization). A typical structure of the table (or database) that needs to capture every transaction detail, such as transaction date and amount, would require an entry for every transaction, and the database designers call it the “normal” state. As I explained in my previous article (“Ranking is the key”), if you would like to rank in terms of customer value, the data record must be on a customer level, as well. If you are ranking households or companies, you would then need to summarize the data on those levels, too.

Now, this summarization (or de-normalization) is not a process of eliminating duplicate entries of names, as you wouldn’t want to throw away any transaction details. If there are multiple orders per person, what is the total number of orders? What is the total amount of spending on an individual level? What would be average spending level per transaction, or per year? If you are allowed to have only one line of entry per person, how would you summarize the purchase dates, as you cannot just add them up? In that case, you can start with the first and last transaction date of each customer. Now, when you have the first and last transaction date for every customer, what would be the tenure of each customer and what would be the number of days since the last purchase? How many days, on average, are there in between orders then? Yes, all these figures are related to basic RFM metrics, but they are far more colorful this way.

The attached exhibit displays a very simple example of a before and after picture of such summarization process. On the left-hand side, there resides a typical order table containing customer ID, order number, order date and transaction amount. If a customer has multiple orders in a given period, an equal number of lines are required to record the transaction details. In real life, other order level information, such as payment method (very predictive, by the way), tax amount, discount or coupon amount and, if applicable, shipping amount would be on this table, as well.

On the right-hand side of the chart, you will find there is only one line per customer. As I mentioned in my previous columns, establishing consistent and accurate customer ID cannot be neglected—for this reason alone. How would you rely on the summary data if one person may have multiple IDs? The customer may have moved to a new address, or shopped from multiple stores or sites, or there could have been errors in data collections. Relying on email address is a big no-no, as we all carry many email addresses. That is why the first step of building a functional marketing database is to go through the data hygiene and consolidation process. (There are many data processing vendors and software packages for it.) Once a persistent customer (or individual) ID system is in place, you can add up the numbers to create customer-level statistics, such as total orders, total dollars, and first and last order dates, as you see in the chart.

Remember R, F, M, P and C
The real fun begins when you combine these numeric summary figures with product, channel and other important categorical variables. Because product (or service) and channel are the most distinctive dividers of customer behaviors, let’s just add P and C to the famous RFM (remember, we are using RFM just as a checklist here), and call it R, F, M, P and C.

Product (rather, product category) is an important separator, as people often show completely different spending behavior for different types of products. For example, you can send me fancy-shmancy fashion catalogs all you want, but I won’t look at it with an intention of purchase, as most men will look at the models and not what they are wearing. So my active purchase history in the sports, home electronics or music categories won’t mean anything in the fashion category. In other words, those so-called “hotline” names should be treated differently for different categories.

Channel information is also important, as there are active online buyers who would never buy certain items, such as apparel or home furnishing products, without physically touching them first. For example, even in the same categories, I would buy guitar strings or golf balls online. But I would not purchase a guitar or a driver without trying them out first. Now, when I say channel, I mean the channel that the customer used to make the purchase, not the channel through which the marketer chose to communicate with him. Channel information should be treated as a two-way street, as no marketer “owns” a customer through a particular channel (refer to “The Future of Online is Offline“).

As an exercise, let’s go back to the basic RFM data and create some actual variables. For “each” customer, we can start with basic RFM measures, as exhibited in the chart:

· Number of Transactions
· Total Dollar Amount
· Number of Days (or Weeks) since the Last Transaction
· Number of Days (or Weeks) since the First Transaction

Notice that the days are counted from today’s point of view (practically the day the database is updated), as the actual date’s significance changes as time goes by (e.g., a day in February would feel different when looked back on from April vs. November). “Recency” is a relative concept; therefore, we should relativize the time measurements to express it.

From these basic figures, we can derive other related variables, such as:

· Average Dollar Amount per Customer
· Average Dollar Amount per Transaction
· Average Dollar Amount per Year
· Lifetime Highest Amount per Item
· Lifetime Lowest Amount per Transaction
· Average Number of Days Between Transactions
· Etc., etc…

Now, imagine you have all these measurements by channels, such as retail, Web, catalog, phone or mail-in, and separately by product categories. If you imagine a gigantic spreadsheet, the summarized table would have fewer numbers of rows, but a seemingly endless number of columns. I will discuss categorical and non-numeric variables in future articles. But for this exercise, let’s just imagine having these sets of variables for all major product categories. The result is that the recency factor now becomes more like “Weeks since Last Online Order”—not just any order. Frequency measurements would be more like “Number of Transactions in Dietary Supplement Category”—not just for any product. Monetary values can be expressed in “Average Spending Level in Outdoor Sports Category through Online Channel”—not just the customer’s average dollar amount, in general.

Why stop there? We may slice and dice the data by offer type, customer status, payment method or time intervals (e.g., lifetime, 24-month, 48-months, etc.) as well. I am not saying that all the RFM variables should be cut out this way, but having “Number of Transaction by Payment Method,” for example, could be very revealing about the customer, as everybody uses multiple payment methods, while some may never use a debit card for a large purchase, for example. All these little measurements become building blocks in predictive modeling. Now, too many variables can also be troublesome. And knowing the balance (i.e., knowing where to stop) comes from the experience and preliminary analysis. That is when experts and analysts should be consulted for this type of uniform variable creation. Nevertheless, the point is that RFM variables are not just three simple measures that happen be a part of the larger transaction data menu. And we didn’t even touch non-transaction based behavioral elements, such as clicks, views, miles or minutes.

The Time Factor
So, if such data summarization is so useful for analytics and modeling, should we always include everything that has been collected since the inception of the database? The answer is yes and no. Sorry for being cryptic here, but it really depends on what your product is all about; how the buyers would relate to it; and what you, as a marketer, are trying to achieve. As for going back forever, there is a danger in that kind of data hoarding, as “Life-to-Date” data always favors tenured customers over new customers who have a relatively short history. In reality, many new customers may have more potential in terms of value than a tenured customer with lots of transaction records from a long time ago, but with no recent activity. That is why we need to create a level playing field in terms of time limit.

If a “Life-to-Date” summary is not ideal for predictive analytics, then where should you place the cutoff line? If you are selling cars or home furnishing products, we may need to look at a 4- to 5-year history. If your products are consumables with relatively short purchase cycles, then a 1-year examination would be enough. If your product is seasonal in nature—like gardening, vacation or heavily holiday-related items, then you may have to look at a minimum of two consecutive years of history to capture seasonal patterns. If you have mixed seasonality or longevity of products (e.g., selling golf balls and golf clubs sets through the same store or site), then you may have to summarize the data with multiple timelines, where the above metrics would be separated by 12 months, 24 months, 48 months, etc. If you have lifetime value models or any time-series models in the plan, then you may have to break the timeline down even more finely. Again, this is where you may need professional guidance, but marketers’ input is equally important.

Analytical Sandbox
Lastly, who should be doing all of this data summary work? I talked about the concept of the “Analytical Sandbox,” where all types of data conversion, hygiene, transformation, categorization and summarization are done in a consistent manner, and analytical activities, such as sampling, profiling, modeling and scoring are done with proper toolsets like SAS, R or SPSS (refer to “It’s All About Ranking“). The short and final answer is this: Do not leave that to analysts or statisticians. They are the main players in that playground, not the architects or developers of it. If you are serious about employing analytics for your business, plan to build the Analytical Sandbox along with the team of analysts.

My goal as a database designer has always been serving the analysts and statisticians with “model-ready” datasets on silver platters. My promise to them has been that the modelers would spend no time fixing the data. Instead, they would be spending their valuable time thinking about the targets and statistical methodologies to fulfill the marketing goals. After all, answers that we seek come out of those mighty—but often elusive—algorithms, and the algorithms are made of data variables. So, in the interest of getting the proper answers fast, we must build lots of building blocks first. And no, simple RFM variables won’t cut it.

Big Data Must Get Smaller

Like many folks who worked in the data business for a long time, I don’t even like the words “Big Data.” Yeah, data is big now, I get it. But so what? Faster and bigger have been the theme in the computing business since the first calculator was invented. In fact, I don’t appreciate the common definition of Big Data that is often expressed in the three Vs: volume, velocity and variety. So, if any kind of data are big and fast, it’s all good? I don’t think so. If you have lots of “dumb” data all over the place, how does that help you? Well, as much as all the clutter that’s been piled on in your basement since 1971. It may yield some profit on an online auction site one day. Who knows? Maybe some collector will pay good money for some obscure Coltrane or Moody Blues albums that you never even touched since your last turntable (Ooh, what is that?) died on you. Those oversized album jackets were really cool though, weren’t they?

Like many folks who worked in the data business for a long time, I don’t even like the words “Big Data.” Yeah, data is big now, I get it. But so what? Faster and bigger have been the theme in the computing business since the first calculator was invented. In fact, I don’t appreciate the common definition of Big Data that is often expressed in the three Vs: volume, velocity and variety. So, if any kind of data are big and fast, it’s all good? I don’t think so. If you have lots of “dumb” data all over the place, how does that help you? Well, as much as all the clutter that’s been piled on in your basement since 1971. It may yield some profit on an online auction site one day. Who knows? Maybe some collector will pay good money for some obscure Coltrane or Moody Blues albums that you never even touched since your last turntable (Ooh, what is that?) died on you. Those oversized album jackets were really cool though, weren’t they?

Seriously, the word “Big” only emphasizes the size element, and that is a sure way to miss the essence of the data business. And many folks are missing even that little point by calling all decision-making activities that involve even small-sized data “Big Data.” It is entirely possible that this data stuff seems all new to someone, but the data-based decision-making process has been with us for a very long time. If you use that “B” word to differentiate old-fashioned data analytics of yesteryear and ridiculously large datasets of the present day, yes, that is a proper usage of it. But we all know most people do not mean it that way. One side benefit of this bloated and hyped up buzzword is data professionals like myself do not have to explain what we do for living for 20 minutes anymore by simply uttering the word “Big Data,” though that is a lot like a grandmother declaring all her grandchildren work on computers for living. Better yet, that magic “B” word sometimes opens doors to new business opportunities (or at least a chance to grab a microphone in non-data-related meetings and conferences) that data geeks of the past never dreamed of.

So, I guess it is not all that bad. But lest we forget, all hypes lead to overinvestments, and all overinvestments leads to disappointments, and all disappointments lead to purging of related personnel and vendors that bear that hyped-up dirty word in their titles or division names. If this Big Data stuff does not yield significant profit (or reduction in cost), I am certain that those investment bubbles will burst soon enough. Yes, some data folks may be lucky enough to milk it for another two or three years, but brace for impact if all those collected data do not lead to some serious dollar signs. I know how the storage and processing cost decreased significantly in recent years, but they ain’t totally free, and related man-hours aren’t exactly cheap, either. Also, if this whole data business is a new concept to an organization, any money spent on the promise of Big Data easily becomes a liability for the reluctant bunch.

This is why I open up my speeches and lectures with this question: “Have you made any money with this Big Data stuff yet?” Surely, you didn’t spend all that money to provide faster toys and nicer playgrounds to IT folks? Maybe the head of IT had some fun with it, but let’s ask that question to CFOs, not CTOs, CIOs or CDOs. I know some colleagues (i.e., fellow data geeks) who are already thinking about a new name for this—”decision-making activities, based on data and analytics”—because many of us will be still doing that “data stuff” even after Big Data cease to be cool after the judgment day. Yeah, that Gangnam Style dance was fun for a while, but who still jumps around like a horse?

Now, if you ask me (though nobody did yet), I’d say the Big Data should have been “Smart Data,” “Intelligent Data” or something to that extent. Because data must provide insights. Answers to questions. Guidance to decision-makers. To data professionals, piles of data—especially the ones that are fragmented, unstructured and unformatted, no matter what kind of fancy names the operating system and underlying database technology may bear—it is just a good start. For non-data-professionals, unrefined data—whether they are big or small—would remain distant and obscure. Offering mounds of raw data to end-users is like providing a painting kit when someone wants a picture on the wall. Bragging about the size of the data with impressive sounding new measurements that end with “bytes” is like counting grains of rice in California in front of a hungry man.

Big Data must get smaller. People want yes/no answers to their specific questions. If such clarity is not possible, probability figures to such questions should be provided; as in, “There’s an 80 percent chance of thunderstorms on the day of the company golf outing,” “An above-average chance to close a deal with a certain prospect” or “Potential value of a customer who is repeatedly complaining about something on the phone.” It is about easy-to-understand answers to business questions, not a quintillion bytes of data stored in some obscure cloud somewhere. As I stated at the end of my last column, the Big Data movement should be about (1) Getting rid of the noise, and (2) Providing simple answers to decision-makers. And getting to such answers is indeed the process of making data smaller and smaller.

In my past columns, I talked about the benefits of statistical models in the age of Big Data, as they are the best way to compact big and complex information in forms of simple answers (refer to “Why Model?”). Models built to predict (or point out) who is more likely to be into outdoor sports, to be a risk-averse investor, to go on a cruise vacation, to be a member of discount club, to buy children’s products, to be a bigtime donor or to be a NASCAR fan, are all providing specific answers to specific questions, while each model score is a result of serious reduction of information, often compressing thousands of variables into one answer. That simplification process in itself provides incredible value to decision-makers, as most wouldn’t know where to cut out unnecessary information to answer specific questions. Using mathematical techniques, we can cut down the noise with conviction.

In model development, “Variable Reduction” is the first major step after the target variable is determined (refer to “The Art of Targeting“). It is often the most rigorous and laborious exercise in the whole model development process, where the characteristics of models are often determined as each statistician has his or her unique approach to it. Now, I am not about to initiate a debate about the best statistical method for variable reduction (I haven’t met two statisticians who completely agree with each other in terms of methodologies), but I happened to know that many effective statistical analysts separate variables in terms of data types and treat them differently. In other words, not all data variables are created equal. So, what are the major types of data that database designers and decision-makers (i.e., non-mathematical types) should be aware of?

In the business of predictive analytics for marketing, the following three types of data make up three dimensions of a target individual’s portrait:

  1. Descriptive Data
  2. Transaction Data / Behavioral Data
  3. Attitudinal Data

In other words, if we get to know all three aspects of a person, it will be much easier to predict what the person is about and/or what the person will do. Why do we need these three dimensions? If an individual has a high income and is living in a highly valued home (demographic element, which is descriptive); and if he is an avid golfer (behavioral element often derived from his purchase history), can we just assume that he is politically conservative (attitudinal element)? Well, not really, and not all the time. Sometimes we have to stop and ask what the person’s attitude and outlook on life is all about. Now, because it is not practical to ask everyone in the country about every subject, we often build models to predict the attitudinal aspect with available data. If you got a phone call from a political party that “assumes” your political stance, that incident was probably not random or accidental. Like I emphasized many times, analytics is about making the best of what is available, as there is no such thing as a complete dataset, even in this age of ubiquitous data. Nonetheless, these three dimensions of the data spectrum occupy a unique and distinct place in the business of predictive analytics.

So, in the interest of obtaining, maintaining and utilizing all possible types of data—or, conversely, reducing the size of data with conviction by knowing what to ignore, let us dig a little deeper:

Descriptive Data
Generally, demographic data—such as people’s income, age, number of children, housing size, dwelling type, occupation, etc.—fall under this category. For B-to-B applications, “Firmographic” data—such as number of employees, sales volume, year started, industry type, etc.—would be considered as descriptive data. It is about what the targets “look like” and, generally, they are frozen in the present time. Many prominent data compilers (or data brokers, as the U.S. government calls them) collect, compile and refine the data and make hundreds of variables available to users in various industry sectors. They also fill in the blanks using predictive modeling techniques. In other words, the compilers may not know the income range of every household, but using statistical techniques and other available data—such as age, home ownership, housing value, and many other variables—they provide their best estimates in case of missing values. People often have some allergic reaction to such data compilation practices siting privacy concerns, but these types of data are not about looking up one person at a time, but about analyzing and targeting groups (or segments) of individuals and households. In terms of predictive power, they are quite effective and results are very consistent. The best part is that most of the variables are available for every household in the country, whether they are actual or inferred.

Other types of descriptive data include geo-demographic data, and the Census Data by the U.S. Census Bureau falls under this category. These datasets are organized by geographic denominations such as Census Block Group, Census Tract, Country or ZIP Code Tabulation Area (ZCTA, much like postal ZIP codes, but not exactly the same). Although they are not available on an individual or a household level, the Census data are very useful in predictive modeling, as every target record can be enhanced with it, even when name and address are not available, and data themselves are very stable. The downside is that while the datasets are free through Census Bureau, the raw datasets contain more than 40,000 variables. Plus, due to the budget cut and changes in survey methods during the past decade, the sample size (yes, they sample) decreased significantly, rendering some variables useless at lower geographic denominations, such as Census Block Group. There are professional data companies that narrowed down the list of variables to manageable sizes (300 to 400 variables) and filled in the missing values. Because they are geo-level data, variables are in the forms of percentages, averages or median values of elements, such as gender, race, age, language, occupation, education level, real estate value, etc. (as in, percent male, percent Asian, percent white-collar professionals, average income, median school years, median rent, etc.).

There are many instances where marketers cannot pinpoint the identity of a person due to privacy issues or challenges in data collection, and the Census Data play a role of effective substitute for individual- or household-level demographic data. In predictive analytics, duller variables that are available nearly all the time are often more valuable than precise information with limited availability.

Transaction Data/Behavioral Data
While descriptive data are about what the targets look like, behavioral data are about what they actually did. Often, behavioral data are in forms of transactions. So many just call it transaction data. What marketers commonly refer to as RFM (Recency, Frequency and Monetary) data fall under this category. In terms of predicting power, they are truly at the top of the food chain. Yes, we can build models to guess who potential golfers are with demographic data, such as age, gender, income, occupation, housing value and other neighborhood-level information, but if you get to “know” that someone is a buyer of a box of golf balls every six weeks or so, why guess? Further, models built with transaction data can even predict the nature of future purchases, in terms of monetary value and frequency intervals. Unfortunately, many who have access to RFM data are using them only in rudimentary filtering, as in “select everyone who spends more than $200 in a gift category during the past 12 months,” or something like that. But we can do so much more with rich transaction data in every stage of the marketing life cycle for prospecting, cultivating, retaining and winning back.

Other types of behavioral data include non-transaction data, such as click data, page views, abandoned shopping baskets or movement data. This type of behavioral data is getting a lot of attention as it is truly “big.” The data have been out of reach for many decision-makers before the emergence of new technology to capture and store them. In terms of predictability, nevertheless, they are not as powerful as real transaction data. These non-transaction data may provide directional guidance, as they are what some data geeks call “a-camera-on-everyone’s-shoulder” type of data. But we all know that there is a clear dividing line between people’s intentions and their commitments. And it can be very costly to follow every breath you take, every move you make, and every step you take. Due to their distinct characteristics, transaction data and non-transaction data must be managed separately. And if used together in models, they should be clearly labeled, so the analysts will never treat them the same way by accident. You really don’t want to mix intentions and commitments.

The trouble with the behavioral data are, (1) they are difficult to compile and manage, (2) they get big; sometimes really big, (3) they are generally confined within divisions or companies, and (4) they are not easy to analyze. In fact, most of the examples that I used in this series are about the transaction data. Now, No. 3 here could be really troublesome, as it equates to availability (or lack thereof). Yes, you may know everything that happened with your customers, but do you know where else they are shopping? Fortunately, there are co-op companies that can answer that question, as they are compilers of transaction data across multiple merchants and sources. And combined data can be exponentially more powerful than data in silos. Now, because transaction data are not always available for every person in databases, analysts often combine behavioral data and descriptive data in their models. Transaction data usually become the dominant predictors in such cases, while descriptive data play the supporting roles filling in the gaps and smoothing out the predictive curves.

As I stated repeatedly, predictive analytics in marketing is all about finding out (1) whom to engage, and (2) if you decided to engage someone, what to offer to that person. Using carefully collected transaction data for most of their customers, there are supermarket chains that achieved 100 percent customization rates for their coupon books. That means no two coupon books are exactly the same, which is a quite impressive accomplishment. And that is all transaction data in action, and it is a great example of “Big Data” (or rather, “Smart Data”).

Attitudinal Data
In the past, attitudinal data came from surveys, primary researches and focus groups. Now, basically all social media channels function as gigantic focus groups. Through virtual places, such as Facebook, Twitter or other social media networks, people are freely volunteering what they think and feel about certain products and services, and many marketers are learning how to “listen” to them. Sentiment analysis falls under that category of analytics, and many automatically think of this type of analytics when they hear “Big Data.”

The trouble with social data is:

  1. We often do not know who’s behind the statements in question, and
  2. They are in silos, and it is not easy to combine such data with transaction or demographic data, due to lack of identity of their sources.

Yes, we can see that a certain political candidate is trending high after an impressive speech, but how would we connect that piece of information to whom will actually donate money for the candidate’s causes? If we can find out “where” the target is via an IP address and related ZIP codes, we may be able to connect the voter to geo-demographic data, such as the Census. But, generally, personally identifiable information (PII) is only accessible by the data compilers, if they even bothered to collect them.

Therefore, most such studies are on a macro level, citing trends and directions, and types of analysts in that field are quite different from the micro-level analysts who deal with behavioral data and descriptive data. Now, the former provide important insights regarding the “why” part of the equation, which is often the hardest thing to predict; while the latter provide answers to “who, what, where and when.” (“Who” is the easiest to answer, and “when” is the hardest.) That “why” part may dictate a product development part of the decision-making process at the conceptual stage (as in, “Why would customers care for a new type of dishwasher?”), while “who, what, where and when” are more about selling the developed products (as in “Let’s sell those dishwashers in the most effective ways.”). So, it can be argued that these different types of data call for different types of analytics for different cycles in the decision-making processes.

Obviously, there are more types of data out there. But for marketing applications dealing with humans, these three types of data complete the buyers’ portraits. Now, depending on what marketers are trying to do with the data, they can prioritize where to invest first and what to ignore (for now). If they are early in the marketing cycle trying to develop a new product for the future, they need to understand why people want something and behave in certain ways. If signing up as many new customers as possible is the immediate goal, finding out who and where the ideal prospects are becomes the most imminent task. If maximizing the customer value is the ongoing objective, then you’d better start analyzing transaction data more seriously. If preventing attrition is the goal, then you will have to line up the transaction data in time series format for further analysis.

The business goals must dictate the analytics, and the analytics call for specific types of data to meet the goals, and the supporting datasets should be in “analytics-ready” formats. Not the other way around, where businesses are dictated by the limitations of analytics, and analytics are hampered by inadequate data clutters. That type of business-oriented hierarchy should be the main theme of effective data management, and with clear goals and proper data strategy, you will know where to invest first and what data to ignore as a decision-maker, not necessarily as a mathematical analyst. And that is the first step toward making the Big Data smaller. Don’t be impressed by the size of the data, as they often blur the big picture and not all data are created equal.

Why Model?

Why model? Uh, because someone is ridiculously good looking, like Derek Zoolander? No, seriously, why model when we have so much data around? The short answer is because we will never know the whole truth. That would be the philosophical answer. Physicists construct models to make new quantum field theories more attractive theoretically and more testable physically. If a scientist already knows the secrets of the universe, well, then that person is on a first-name basis with God Almighty, and he or she doesn’t need any models to describe things like particles or strings. And the rest of us should just hope the scientist isn’t one of those evil beings in “Star Trek.”

Why model? Uh, because someone is ridiculously good looking, like Derek Zoolander? No, seriously, why model when we have so much data around?

The short answer is because we will never know the whole truth. That would be the philosophical answer. Physicists construct models to make new quantum field theories more attractive theoretically and more testable physically. If a scientist already knows the secrets of the universe, well, then that person is on a first-name basis with God Almighty, and he or she doesn’t need any models to describe things like particles or strings. And the rest of us should just hope the scientist isn’t one of those evil beings in “Star Trek.”

Another answer to “why model?” is because we don’t really know the future, not even the immediate future. If some object is moving toward a certain direction at a certain velocity, we can safely guess where it will end up in one hour. Then again, nothing in this universe is just one-dimensional like that, and there could be a snowstorm brewing up on its path, messing up the whole trajectory. And that weather “forecast” that predicted the snowstorm is a result of some serious modeling, isn’t it?

What does all this mean for the marketers who are not necessarily masters of mathematics, statistics or theoretical physics? Plenty, actually. And the use of models in marketing goes way back to the days of punch cards and mainframes. If you are too young to know what those things are, well, congratulations on your youth, and let’s just say that it was around the time when humans first stepped on the moon using a crude rocket ship equipped with less computing power than an inexpensive passenger car of the modern days.

Anyhow, in that ancient time, some smart folks in the publishing industry figured that they would save tons of money if they could correctly “guess” who the potential buyers were “before” they dropped any expensive mail pieces. Even with basic regression models—and they only had one or two chances to get it right with glacially slow tools before the all-too-important Christmas season came around every year—they could safely cut the mail quantity by 80 percent to 90 percent. The savings added up really fast by not talking to everyone.

Fast-forward to the 21st Century. There is still a beauty of knowing who the potential buyers are before we start engaging anyone. As I wrote in my previous columns, analytics should answer:

1. To whom you should be talking; and
2. What you should offer once you’ve decided to engage someone.

At least the first part will be taken care of by knowing who is more likely to respond to you.

But in the days when the cost of contacting a person through various channels is dropping rapidly, deciding to whom to talk can’t be the only reason for all this statistical work. Of course not. There are plenty more reasons why being a statistician (or a data scientist, nowadays) is one of the best career choices in this century.

Here is a quick list of benefits of employing statistical models in marketing. Basically, models are constructed to:

  • Reduce cost by contacting prospects more wisely
  • Increase targeting accuracy
  • Maintain consistent results
  • Reveal hidden patterns in data
  • Automate marketing procedures by being more repeatable
  • Expand the prospect universe while minimizing the risk
  • Fill in the gaps and summarize complex data into an easy-to-use format—A must in the age of Big Data
  • Stay relevant to your customers and prospects

We talked enough about the first point, so let’s jump to the second one. It is hard to argue about the “targeting accuracy” part, though there still are plenty of non-believers in this day and age. Why are statistical models more accurate than someone’s gut feeling or sheer guesswork? Let’s just say that in my years of dealing with lots of smart people, I have not met anyone who can think about more than two to three variables at the same time, not to mention potential interactions among them. Maybe some are very experienced in using RFM and demographic data. Maybe they have been reasonably successful with choices of variables handed down to them by their predecessors. But can they really go head-to-head against carefully constructed statistical models?

What is a statistical model, and how is it built? In short, a model is a mathematical expression of “differences” between dichotomous groups. Too much of a mouthful? Just imagine two groups of people who do not overlap. They may be buyers vs. non-buyers; responders vs. non-responders; credit-worthy vs. not-credit-worthy; loyal customers vs. attrition-bound, etc. The first step in modeling is to define the target, and that is the most important step of all. If the target is hanging in the wrong place, you will be shooting at the wrong place, no matter how good your rifle is.

And the target should be expressed in mathematical terms, as computers can’t read our minds, not just yet. Defining the target is a job in itself:

  • If you’re going after frequent flyers, how frequent is frequent enough for you? Five times a year or 10 times a year? Or somewhere in between? Or should it remain continuous?
  • What if the target is too small or too large? What then?
  • If you are looking for more valuable prospects, how would you express that? In terms of average spending, lifetime spending or sheer number of transactions?
  • What if there is an inverse relationship between frequency and dollar spending (i.e., high spenders shopping infrequently)?
  • And what would be the borderline number to be “valuable” in all this?

Once the target is set, after much pondering, then the job is to select the variables that describe the “differences” between the two groups. For example, I know how much marketers love to use income variables in various situations. But if that popular variable does not explain the differences between the two groups (target and non-target), the mathematics will mercilessly throw it out. This rigorous exercise of examining hundreds or even thousands of variables is one of the most critical steps, during which many variables go through various types of transformations. Statisticians have different preferences in terms of ideal numbers of variables in a model, while non-statisticians like us don’t need to be too concerned, as long as the resultant model works. Who cares if a cat is white or black, as long as it catches mice?

Not all selected variables are equally important in model algorithms, either. More powerful variables will be assigned with higher weight, and the sum of these weighted values is what we call model score. Now, non-statisticians who have been slightly allergic to math since the third grade only need to know that the higher the score, the more likely the record in question is to be like the target. To make the matter even simpler, let’s just say that you want higher scores over lower scores. If you are a salesperson, just call the high-score prospects first. And would you care how many variables are packed into that score, for as long as you get the good “Glengarry Glen Ross” leads on top?

So, let me ask again. Does this sound like something a rudimentary selection rule with two to three variables can beat when it comes to identifying the right target? Maybe someone can get lucky once or twice, but not consistently.

That leads to the next point, “consistency.” Because models do not rely on a few popular variables, they are far less volatile than simple selection rules or queries. In this age of Big Data, there are more transaction and behavioral data in the mix than ever, and they are far more volatile than demographic and geo-demographic data. Put simply, people’s purchasing behavior and preferences change much faster than family composition or their income, and that volatility factor calls for more statistical work. Plus, all facets of marketing are now more about measurable results (ah, that dreaded ROI, or “Roy,” the way I call it), and the businesses call for consistent hitters over one-hit wonders.

“Revealing hidden patterns in data” is my favorite. When marketers are presented with thousands of variables, I see a majority of them just sticking to a few popular ones all the time. Some basic recency and frequency data are there, and among hundreds of demographic variables, the list often stops after income, age, gender, presence of children, and some regional variables. But seriously, do you think that the difference between a luxury car buyer and an SUV buyer is just income and age? You see, these variables are just the ones that human minds are accustomed to. Mathematics do not have such preconceived notions. Sticking to a few popular variables is like children repeatedly using three favorite colors out of a whole box of crayons.

I once saw a neighborhood-level U.S. Census variable called “% Households with Septic Tanks” in a model built for a high-end furniture catalog. Really, the variable was “percentage of houses with septic tanks in the neighborhood.” Then I realized it made a lot of sense. That variable was revealing how far away that neighborhood was located in comparison to populous city centers. As the percentage of septic tanks increased, the further away the residents were from the city center. And maybe those folks who live in scarcely populated areas were more likely to shop for furniture through catalogs than the folks who live closer to commercial areas.

This is where we all have that “aha” moment. But you and I will never pick that variable in anything that we do, not in million years, no matter how effective it may be in finding the target prospects. The word “septic” may scare some people off at “hello.” In any case, modeling procedures reveal hidden connections like that all of the time, and that is a very important function in data-rich environments. Otherwise, we will not know what to throw out without fear, and the databases will continuously become larger and more unusable.

Moving on to the next points, “Repeatable” and “Expandable” are somewhat related. Let’s say a marketer has been using a very innovative selection logic that she came across almost by accident. In pursuing special types of wealthy people, she stumbled upon a piece of data called “owner of swimming pool.” Now, she may have even had a few good runs with it, too. But eventually, that success will lead to the question of:

1. Having to repeat that success again and again; and
2. Having to expand that universe, when the “known” universe of swimming pool owners become depleted or saturated.

Ah, the chagrin of a one-hit-wonder begins.

Use of statistical models, with help of multiple variables and scalable scoring, would avoid all of those issues. You want to expand the prospect universe? No trouble. Just dial down the scores on the scale a little further. We can even measure the risk of reaching into the lower-scoring groups. And you don’t have to worry about coverage issues related to a few variables, as those won’t be the only ones in the model. Want to automate the selection process? No problem there, as using a score, which is a summary of key predictors, is far simpler than having to carry a long list of data variables into any automated system.

Now, that leads to the next point, “Filling in the gaps and summarizing the complex data into an easy-to-use format.” In the age of ubiquitous and “Big” data, this is the single-most important point, way beyond the previous examples for traditional 1-to-1 marketing applications. We are definitely going through massive data overloads everywhere, and someone better refine the data and provide some usable answers.

As I mentioned earlier, we build models because we will never know the whole truth. I believe that the Big Data movement should be all about:

1. Filtering the noise from valuable information; and
2. Filling the gaps.

“Gaps,” you say? Believe me, there are plenty of gaps in any dataset, big or small.

When information continues to get piled on, the resultant database may look big. And they are physically large. But in marketing, as I repeatedly emphasized in my previous columns, the data must be realigned to “buyer-centric” formats, with every data point describing each individual, as marketing is all about people.

Sure, you may have tons of mobile phone-related data. In fact, it could be quite huge in size. But let me turn that upside down for you (more like sideways-up, in practice). Now, try to describe everyone in your footprint in terms of certain activities. Say, “every smart phone owner who used more than 80 percent of his or her monthly data allowance on the average for the past 12 months, regardless of the carrier.” Hey, don’t blame me for asking these questions just because it’s inconvenient for data handlers to answer them. Some marketers would certainly benefit from information like that, and no one cares about just bits and pieces of data, other than for some interesting tidbits at a party.

Here’s the main trouble when you start asking buyer-related questions like that. Once we try to look at the world from the “buyer-centric” point of view, we will realize there are tons of missing data (i.e., a whole bunch of people with not much information). It may be that you will never get this kind of data from all carriers. Maybe not everyone is tracked this way. In terms of individuals, you may end up with less than 10 percent in the database with mobile information attached to them. In fact, many interesting variables may have less than 1 percent coverage. Holes are everywhere in so-called Big Data.

Models can fill in those blanks for you. For all those data compilers who sell age and income data for every household in the country, do you believe that they really “know” everyone’s age and income? A good majority of the information is based on carefully constructed models. And there is nothing wrong with that.

If you don’t get to “know” something, we can get to a “likelihood” score—of “being like” that something. And in that world, every measurement is on a scale, with no missing values. For example, the higher the score of a model built for a telecommunication company, the more likely that the prospect is going to use a high-speed data plan, or the international long distance services, depending on the purpose of the model. Or the more likely the person will buy sports packages via cable or satellite. Or the person is more likely to subscribe to premium movie channels. Etc., etc. With scores like these, a marketer can initiate the conversation with—not just talking to—a particular prospect with customized product packages in his hand.

And that leads us to the final point in all this, “Staying relevant to your customers and prospects.” That is what Big Data should be all about—at least for us marketers. We know plenty about a lot of people. And they are asking us why we are still so random about marketing messages. With all these data that are literally floating around, marketers can do so much better. But not without statistical models that fill in the gaps and turn pieces of data into marketing-ready answers.

So, why model? Because a big pile of information doesn’t provide answers on its own, and that pile has more holes than Swiss cheese if you look closely. That’s my final answer.