Smart Data – Not Big Data

As a concerned data professional, I am already plotting an exit strategy from this Big Data hype. Because like any bubble, it will surely burst. That inevitable doomsday could be a couple of years away, but I can feel it coming. At the risk of sounding too much like Yoda the Jedi Grand Master, all hypes lead to over-investments, all over-investments lead to disappointments, and all disappointments lead to blames. Yes, in a few years, lots of blames will go around, and lots of heads will roll.

As a concerned data professional, I am already plotting an exit strategy from this Big Data hype. Because like any bubble, it will surely burst. That inevitable doomsday could be a couple of years away, but I can feel it coming. At the risk of sounding too much like Yoda the Jedi Grand Master, all hypes lead to over-investments, all over-investments lead to disappointments, and all disappointments lead to blames. Yes, in a few years, lots of blames will go around, and lots of heads will roll.

So, why would I stay on the troubled side? Well, because, for now, this Big Data thing is creating lots of opportunities, too. I am writing this on my way back from Seoul, Korea, where I presented this Big Data idea nine times in just two short weeks, trotting from large venues to small gatherings. Just a few years back, I used to have a hard time explaining what I do for living. Now, I just have to say “Hey, I do this Big Data thing,” and the doors start to open. In my experience, this is the best “Open Sesame” moment for all data specialists. But it will last only if we play it right.

Nonetheless, I also know that I will somehow continue to make living setting data strategies, fixing bad data, designing databases and leading analytical activities, even after the hype cools down. Just with a different title, under a different banner. I’ve seen buzzwords come and go, and this data business has been carried on by the people who cut through each hype (and gargantuan amount of BS along with it) and create real revenue-generating opportunities. At the end of the day (I apologize for using this cliché), it is all about the bottom line, whether it comes from a revenue increase or cost reduction. It is never about the buzzwords that may have created the business opportunities in the first place; it has always been more about the substance that turned those opportunities into money-making machines. And substance needs no fancy title or buzzwords attached to it.

Have you heard Google or Amazon calling themselves a “Big Data” companies? They are the ones with sick amounts of data, but they also know that it is not about the sheer amount of data, but it is all about the user experience. “Wannabes” who are not able to understand the core values often hang onto buzzwords and hypes. As if Big Data, Cloud Computing or coding language du jour will come and save the day. But they are just words.

Even the name “Big Data” is all wrong, as it implies that bigger is always better. The 3 Vs of Big Data—volume, velocity and variety—are also misleading. That could be a meaningful distinction for existing data players, but for decision-makers, it gives a notion that size and speed are the ultimate quest. But for the users, small is better. They don’t have time to analyze big sets of data. They need small answers in fun size packages. Plus, why is big and fast new? Since the invention of modern computers, has there been any year when the processing speed did not get faster and storage capacity did not get bigger?

Lest we forget, it is the software industry that came up with this Big Data thing. It was created as a marketing tagline. We should have read it as, “Yes, we can now process really large amounts of data, too,” not as, “Big Data will make all your dreams come true.” If you are in the business of selling toolsets, of course, that is how you present your product. If guitar companies keep emphasizing how hard it is to be a decent guitar player, would that help their businesses? It is a lot more effective to say, “Hey, this is the same guitar that your guitar hero plays!” But you don’t become Jeff Beck just because you bought a white Fender Stratocaster with a rosewood neck. The real hard work begins “after” you purchase a decent guitar. However, this obvious connection is often lost in the data business. Toolsets never provide solutions on their own. They may make your life easier, but you’d still have to formulate the question in a logical fashion, and still have to make decisions based on provided data. And harnessing meanings out of mounds of data requires training of your mind, much like the way musicians practice incessantly.

So, before business people even consider venturing into this Big Data hype, they should ask themselves “Why data?” What are burning questions that you are trying to solve with the data? If you can’t answer this simple question, then don’t jump into it. Forget about it. Don’t get into it just because everyone else seems to be getting into it. Yeah, it’s a big party, but why are you going there? Besides, if you formulate the question properly, often you will find that you don’t need Big Data all the time. If fact, Big Data can be a terrible detour if your question can be answered by “small” data. But that happens all the time, because people approach their business questions through the processes set by the toolsets. Big Data should be about the business, not about the IT or data.

Smart Data, Not Big Data
So, how do we get over this hype? All too often, perception rules, and a replacement word becomes necessary to summarize the essence of the concept for the general public. In my opinion, “Big Data” should have been “Smart Data.” Piles of unorganized dumb data aren’t worth a damn thing. Imagine a warehouse full of boxes with no labels, collecting dust since 1943. Would you be impressed with the sheer size of the warehouse? Great, the ark that Indiana Jones procured (or did he?) may be stored in there somewhere. But if no one knows where it is—or even if it can be located, if no one knows what to do with it—who cares?

Then, how do data get smarter? Smart data are bite-sized answers to questions. A thousand variables could have been considered to provide the weather forecast that calls for a “70 percent chance of scattered showers in the afternoon,” but that one line that we hear is the smart piece of data. Not the list of all the variables that went into the formula that created that answer. Emphasizing the raw data would be like giving paints and brushes to a person who wants a picture on the wall. As in, “Hey, here are all the ingredients, so why don’t you paint the picture and hang it on the wall?” Unfortunately, that is how the Big Data movement looks now. And too often, even the ingredients aren’t all that great.

I visit many companies only to find that the databases in question are just messy piles of unorganized and unstructured data. And please do not assume that such disarrays are good for my business. I’d rather spend my time harnessing meanings out of data and creating values, not taking care of someone else’s mess all the time. Really smart data are small, concise, clean and organized. Big Data should only be seen in “Behind the Scenes” types of documentaries for manias, not for everyday decision-makers.

I have been already saying that Big Data must get smaller for some time (refer to “Big Data Must Get Smaller“) and I would repeat it until it becomes a movement on its own. The Big Data movement must be about:

  1. Cutting down the noise
  2. Providing the answers

There is too much noise in the data, and cutting it out is the first step toward making the data smaller and smarter. The trouble is that the definition of “noise” is not static. Rock music that I grew up with was certainly a noise to my parents’ generation. In turn, some music that my kids listen to is pure noise to me. Likewise, “product color,” which is essential for a database designed for an inventory management system, may or may not be noise if the goal is to sell more apparel items. In such cases, more important variables could be style, brand, price range, target gender, etc., but color could be just peripheral information at best, or even noise (as in, “Uh, she isn’t going to buy just red shoes all the time?”). How do we then determine the differences? First, set the clear goals (as in, “Why are we playing with the data to begin with?”), define the goals using logical expressions, and let mathematics take care of it. Now you can drop the noise with conviction (even if it may look important to human minds).

If we continue with that mathematical path, we would reach the second part, which is “providing answers to the question.” And the smart answers are in the forms of yes/no, probability figures or some type of scores. Like in the weather forecast example, the question would be “chance of rain on a certain day” and the answer would be “70 percent.” Statistical modeling is not easy or simple, but it is the essential part of making the data smarter, as models are the most effective way to summarize complex and abundant data into compact forms (refer to “Why Model?”).

Most people do not have degrees in mathematics or statistics, but they all know what to do with a piece of information such as “70 percent chance of rain” on the day of a company outing. Some may complain that it is not a definite yes/no answer, but all would agree that providing information in this form is more humane than dumping all the raw data onto users. Sales folks are not necessarily mathematicians, but they would certainly appreciate scores attached to each lead, as in “more or less likely to close.” No, that is not a definite answer, but now sales people can start calling the leads in the order of relative importance to them.

So, all the Big Data players and data scientists must try to “humanize” the data, instead of bragging about the size of the data, making things more complex, and providing irrelevant pieces of raw data to users. Make things simpler, not more complex. Some may think that complexity is their job security, but I strongly disagree. That is a sure way to bring down this Big Data movement to the ground. We are already living in a complex world, and we certainly do not need more complications around us (more on “How to be a good data scientist” in a future article).

It’s About the Users, Too
On the flip side, the decision-makers must change their attitude about the data, as well.

1. Define the goals first: The main theme of this series has been that the Big Data movement is about the business, not IT or data. But I’ve seen too many business folks who would so willingly take a hands-off approach to data. They just fund the database; do not define clear business goals to developers; and hope to God that someday, somehow, some genius will show up and clear up the mess for them. Guess what? That cavalry is never coming if you are not even praying properly. If you do not know what problems you want to solve with data, don’t even get started; you will get to nowhere really slowly, bleeding lots of money and time along the way.

2. Take the data seriously: You don’t have to be a scientist to have a scientific mind. It is not ideal if someone blindly subscribes anything computers spew out (there are lots of inaccurate information in databases; refer to “Not All Databases Are Created Equal.”). But too many people do not take data seriously and continue to follow their gut feelings. Even if your customer profile coming out of a serious analysis does not match with your preconceived notions, do not blindly reject it; instead, treat it as a newly found gold mine. Gut feelings are even more overrated than Big Data.

3. Be logical: Illogical questions do not lead anywhere. There is no toolset that reads minds—at least not yet. Even if we get to have such amazing computers—as seen on “Star Trek” or in other science fiction movies—you would still have to ask questions in a logical fashion for them to be effective. I am not asking decision-makers to learn how to code (or be like Mr. Spock or his loyal follower, Dr. Sheldon Cooper), but to have some basic understanding of logical expressions and try to learn how analysts communicate with computers. This is not data geek vs. non-geek world anymore; we all have to be a little geekier. Knowing Boolean expressions may not be as cool as being able to throw a curve ball, but it is necessary to survive in the age of information overload.

4. Shoot for small successes: Start with a small proof of concept before fully investing in large data initiatives. Even with a small project, one gets to touch all necessary steps to finish the job. Understanding the flow of information is as important as each specific step, as most breakdowns occur in between steps, due to lack of proper connections. There was Gemini program before Apollo missions. Learn how to dock spaceships in space before plotting the chart to the moon. Often, over-investments are committed when the discussion is led by IT. Outsource even major components in the beginning, as the initial goal should be mastering the flow of things.

5. Be buyer-centric: No customer is bound by the channel of the marketer’s choice, and yet, may businesses act exactly that way. No one is an online person just because she did not refuse your email promotions yet (refer to “The Future of Online is Offline“). No buyer is just one dimensional. So get out of brand-, division-, product- or channel-centric mindsets. Even well-designed, buyer-centric marketing databases become ineffective if users are trapped in their channel- or division-centric attitudes, as in “These email promotions must flow!” or “I own this product line!” The more data we collect, the more chances marketers will gain to impress their customers and prospects. Do not waste those opportunities by imposing your own myopic views on them. Big Data movement is not there to fortify marketers’ bad habits. Thanks to the size of the data and speed of machines, we are now capable of disappointing a lot of people really fast.

What Did This Hype Change?
So, what did this Big Data hype change? First off, it changed people’s attitudes about the data. Some are no longer afraid of large amounts of information being thrown at them, and some actually started using them in their decision-making processes. Many realized that we are surrounded by numbers everywhere, not just in marketing, but also in politics, media, national security, health care and the criminal justice system.

Conversely, some people became more afraid—often with good reasons. But even more often, people react based on pure fear that their personal information is being actively exploited without their consent. While data geeks are rejoicing in the age of open source and cloud computing, many more are looking at this hype with deep suspicions, and they boldly reject storing any personal data in those obscure “clouds.” There are some people who don’t even sign up for EZ Pass and voluntarily stay on the long lane to pay tolls in the old, but untraceable way.

Nevertheless, not all is lost in this hype. The data got really big, and types of data that were previously unavailable, such as mobile and social data, became available to many marketers. Focus groups are now the size of Twitter followers of the company or a subject matter. The collection rate of POS (point of service) data has been increasingly steady, and some data players became virtuosi in using such fresh and abundant data to impress their customers (though some crossed that “creepy” line inadvertently). Different types of data are being used together now, and such merging activities will compound the predictive power even further. Analysts are dealing with less missing data, though no dataset would ever be totally complete. Developers in open source environments are now able to move really fast with new toolsets that would just run on any device. Simply, things that our forefathers of direct marketing used to take six months to complete can be done in few hours, and in the near future, maybe within a few seconds.

And that may be a good thing and a bad thing. If we do this right, without creating too many angry consumers and without burning holes in our budgets, we are currently in a position to achieve great many things in terms of predicting the future and making everyone’s lives a little more convenient. If we screw it up badly, we will end up creating lots of angry customers by abusing sensitive data and, at the same time, wasting a whole lot of investors’ money. Then this Big Data thing will go down in history as a great money-eating hype.

We should never do things just because we can; data is a powerful tool that can hurt real people. Do not even get into it if you don’t have a clear goal in terms of what to do with the data; it is not some piece of furniture that you buy just because your neighbor bought it. Living with data is a lifestyle change, and it requires a long-term commitment; it is not some fad that you try once and give up. It is a continuous loop where people’s responses to marketer’s data-based activities create even more data to be analyzed. And that is the only way it keeps getting better.

There Is No Big Data
And all that has nothing to do with “Big.” If done right, small data can do plenty. And in fact, most companies’ transaction data for the past few years would easily fit in an iPhone. It is about what to do with the data, and that goal must be set from a business point of view. This is not just a new playground for data geeks, who may care more for new hip technologies that sound cool in their little circle.

I recently went to Brazil to speak at a data conference called QIBRAS, and I was pleasantly surprised that the main theme of it was the quality of the data, not the size of the data. Well, at least somewhere in the world, people are approaching this whole thing without the “Big” hype. And if you look around, you will not find any successful data players calling this thing “Big Data.” They just deal with small and large data as part of their businesses. There is no buzzword, fanfare or a big banner there. Because when something is just part of your everyday business, you don’t even care what you call it. You just do. And to those masters of data, there is no Big Data. If Google all of a sudden starts calling itself a Big Data company, it would be so uncool, as that word would seriously limit it. Think about that.

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.”

Chicken or the Egg? Data or Analytics?

I just saw an online discussion about the role of a chief data officer, whether it should be more about data or analytics. My initial response to that question is “neither.” A chief data officer must represent the business first.

I just saw an online discussion about the role of a chief data officer, whether it should be more about data or analytics. My initial response to that question is “neither.” A chief data officer must represent the business first. And I had the same answer when such a title didn’t even exist and CTOs or other types of executives covered that role in data-rich environments. As soon as an executive with a seemingly technical title starts representing the technology, that business is doomed. (Unless, of course, the business itself is about having fun with the technology. How nice!)

Nonetheless, if I really have to pick just one out of the two choices, I would definitely pick the analytics over data, as that is the key to providing answers to business questions. Data and databases must be supporting that critical role of analytics, not the other way around. Unfortunately, many organizations are completely backward about it, where analysts are confined within the limitations of database structures and affiliated technologies, and the business owners and decision-makers are dictated to by the analysts and analytical tool sets. It should be the business first, then the analytics. And all databases—especially marketing databases—should be optimized for analytical activities.

In my previous columns, I talked about the importance of marketing databases and statistical modeling in the age of Big Data; not all depositories of information are necessarily marketing databases, and statistical modeling is the best way to harness marketing answers out of mounds of accumulated data. That begs for the next question: Is your marketing database model-ready?

When I talk about the benefits of statistical modeling in data-rich environments (refer to my previous column titled “Why Model?”), I often encounter folks who list reasons why they do not employ modeling as part of their normal marketing activities. If I may share a few examples here:

  • Target universe is too small: Depending on the industry, the prospect universe and customer base are sometimes very small in size, so one may decide to engage everyone in the target group. But do you know what to offer to each of your prospects? Customized offers should be based on some serious analytics.
  • Predictive data not available: This may have been true years back, but not in this day and age. Either there is a major failure in data collection, or collected data are too unstructured to yield any meaningful answers. Aren’t we living in the age of Big Data? Surely we should all dig deeper.
  • 1-to-1 marketing channels not in plan: As I repeatedly said in my previous columns, “every” channel is, or soon will be, a 1-to-1 channel. Every audience is secretly screaming, “Entertain us!” And customized customer engagement efforts should be based on modeling, segmentation and profiling.
  • Budget doesn’t allow modeling: If the budget is too tight, a marketer may opt in for some software solution instead of hiring a team of statisticians. Remember that cookie-cutter models out of software packages are still better than someone’s intuitive selection rules (i.e., someone’s “gut” feeling).
  • The whole modeling process is just too painful: Hmm, I hear you. The whole process could be long and difficult. Now, why do you think it is so painful?

Like a good doctor, a consultant should be able to identify root causes based on pain points. So let’s hear some complaints:

  • It is not easy to find “best” customers for targeting
  • Modelers are fixing data all the time
  • Models end up relying on a few popular variables, anyway
  • Analysts are asking for more data all the time
  • It takes too long to develop and implement models
  • There are serious inconsistencies when models are applied to the database
  • Results are disappointing
  • Etc., etc…

I often get called in when model-based marketing efforts yield disappointing results. More often than not, the opening statement in such meetings is that “The model did not work.” Really? What is interesting is that in more than nine times out of 10 cases like that, the models are the only elements that seem to have been done properly. Everything else—from pre-modeling steps, such as data hygiene, conversion, categorization, and summarization; to post-modeling steps, such as score application and validation—often turns out to be the root cause of all the troubles, resulting in pain points listed here.

When I speak at marketing conferences, talking about this subject of this “model-ready” environment, I always ask if there are statisticians and analysts in the audience. Then I ask what percentage of their time goes into non-statistical activities, such as data preparation and remedying data errors. The absolute majority of them say they spend of 80 percent to 90 percent of their time fixing the data, devoting the rest to the model development work. You don’t need me to tell you that something is terribly wrong with this picture. And I am pretty sure that none of those analysts got their PhDs and master’s degrees in statistics to spend most of their waking hours fixing the data. Yeah, I know from experience that, in this data business, the last guy who happens to touch the dataset always ends up being responsible for all errors made to the file thus far, but still. No wonder it is often quoted that one of the key elements of being a successful data scientist is the programming skill.

When you provide datasets filled with unstructured, incomplete and/or missing data, diligent analysts will devote their time to remedying the situation and making the best out of what they have received. I myself often tell newcomers that analytics is really about making the best of what you’ve got. The trouble is that such data preparation work calls for a different set of skills that have nothing to do with statistics or analytics, and most analysts are not that great at programming, nor are they trained for it.

Even if they were able to create a set of sensible variables to play with, here comes the bigger trouble; what they have just fixed is just a “sample” of the database, when the models must be applied to the whole thing later. Modern databases often contain hundreds of millions of records, and no analyst in his or her right mind uses the whole base to develop any models. Even if the sample is as large as a few million records (an overkill, for sure) that would hardly be the entire picture. The real trouble is that no model is useful unless the resultant model scores are available on every record in the database. It is one thing to fix a sample of a few hundred thousand records. Now try to apply that model algorithm to 200 million entries. You see all those interesting variables that analysts created and fixed in the sample universe? All that should be redone in the real database with hundreds of millions of lines.

Sure, it is not impossible to include all the instructions of variable conversion, reformat, edit and summarization in the model-scoring program. But such a practice is the No. 1 cause of errors, inconsistencies and serious delays. Yes, it is not impossible to steer a car with your knees while texting with your hands, but I wouldn’t call that the best practice.

That is why marketing databases must be model-ready, where sampling and scoring become a routine with minimal data transformation. When I design a marketing database, I always put the analysts on top of the user list. Sure, non-statistical types will still be able to run queries and reports out of it, but those activities should be secondary as they are lower-level functions (i.e., simpler and easier) compared to being “model-ready.”

Here is list of prerequisites of being model-ready (which will be explained in detail in my future columns):

  • All tables linked or merged properly and consistently
  • Data summarized to consistent levels such as individuals, households, email entries or products (depending on the ranking priority by the users)
  • All numeric fields standardized, where missing data and zero values are separated
  • All categorical data edited and categorized according to preset business rules
  • Missing data imputed by standardized set of rules
  • All external data variables appended properly

Basically, the whole database should be as pristine as the sample datasets that analysts play with. That way, sampling should take only a few seconds, and applying the resultant model algorithms to the whole base would simply be the computer’s job, not some nerve-wrecking, nail-biting, all-night baby-sitting suspense for every update cycle.

In my co-op database days, we designed and implemented the core database with this model-ready philosophy, where all samples were presented to the analysts on silver platters, with absolutely no need for fixing the data any further. Analysts devoted their time to pondering target definitions and statistical methodologies. This way, each analyst was able to build about eight to 10 “custom” models—not cookie-cutter models—per “day,” and all models were applied to the entire database with more than 200 million individuals at the end of each day (I hear that they are even more efficient these days). Now, for the folks who are accustomed to 30-day model implementation cycle (I’ve seen as long as 6-month cycles), this may sound like a total science fiction. And I am not even saying that all companies need to build and implement that many models every day, as that would hardly be a core business for them, anyway.

In any case, this type of practice has been in use way before the words “Big Data” were even uttered by anyone, and I would say that such discipline is required even more desperately now. Everyone is screaming for immediate answers for their questions, and the questions should be answered in forms of model scores, which are the most effective and concise summations of all available data. This so-called “in-database” modeling and scoring practice starts with “model-ready” database structure. In the upcoming issues, I will share the detailed ways to get there.

So, here is the answer for the chicken-or-the-egg question. It is the business posing the questions first and foremost, then the analytics providing answers to those questions, where databases are optimized to support such analytical activities including predictive modeling. For the chicken example, with the ultimate goal of all living creatures being procreation of their species, I’d say eggs are just a means to that end. Therefore, for a business-minded chicken, yeah, definitely the chicken before the egg. Not that I’ve seen too many logical chickens.