Models Are Built, But the Job Isn’t Done Yet

In my line of business – data and analytics consulting and coaching – I often recommend some modeling work when confronted with complex targeting challenges. Through this series, I’ve shared many reasons why modeling becomes a necessity in data-rich environments (refer to “Why Model?”).

The history of model-based targeting goes back to the 1960’s, but what is the number one reason to employ modeling techniques these days? We often have too much information, way beyond the cognitive and arithmetical capacities of our brains. Most of us mortals cannot effectively consider more than two or three variables at a time. Conversely, machines don’t have such limitations when it comes to recognizing patterns among countless data variables. Subsequent marketing automation is just an added bonus.

We operate under a basic assumption that model-based targeting (with deep data) should outperform some man-made rules (with a handful of information). At times, however, I get calls as campaign results prove otherwise. Sometimes campaign segments selected by models show worse response rates than randomly selected test groups do.

When such disappointing results happen, most decision makers casually say, “The model did not work.” That may be true, but more often than not, I find that something went wrong “before” or “after” the modeling process. (Refer to “Know What to Automate With Machine Learning”, where I list major steps concerning the “before” of model-based targeting).

If the model is developed in an “analytics-ready” environment where most input errors are eradicated, then here are some common mishaps in post-modeling stages to consider.

Mishap #1: The Model Is Applied to the Wrong Universe

Model algorithm is nothing but a mathematical expression between target and comparison universes. Yes, setting up the right target is the key for success in any modeling, but defining a proper comparison universe is equally important. And the comparison group must represent the campaign universe to which the resultant model is applied.

Sometimes such universes are defined by a series of pre-selection rules before the modeling even begins. For example, the campaign universes may be set by region (or business footprint), gender of the target, availability of email address or digital ID, income level, home ownership, etc. Once set, the rules must be enforced throughout the campaign execution.

What if the rules that define the modeling universe are even slightly different from the actual campaign universe? The project may be doomed from the get-go.

For example, do not expect that models developed within a well-established business footprint will be equally effective in relatively new prospecting areas. Such expansion calls for yet another set of models, as target prospects are indeed in a different world.

If there are multiple distinct segments in the customer base, we often develop separate models within each key segment. Don’t even think about applying a model developed in one specific segment to another, just because they may look similar on the surface. And if you do something like that, don’t blame the modeler later.

Mishap #2: The Model Is Used Outside Design Specification

Even in the same modeling universe, we may develop multiple types of models for different purposes. Some models may be designed to predict future lifetime value of customers, while others are to estimate campaign responsiveness. In this example, customer value and campaign responsiveness may actually be inversely related (e.g., potential high value customers less likely to be responsive to email campaigns).

If multiple response models are built for specific channels, do not use them interchangeably. Each model should be describing distinct channel behaviors, not just general responsiveness to given offers or products.

I’ve seen a case where a cruise ship company used an affinity model specifically designed for a seasonal European line for general purposes in the name of cost savings. The result? It would have been far more cost effective developing another model than having to deal with the fallout from ineffective campaigns. Modeling cost is often a small slice in the whole pie of campaign expenses. Don’t get stingy on analytics and call for help when in doubt.

Mishap #3: There Are Scoring Errors

Applying a model algorithm to a validation sample is relatively simple, as such samples are not really large. Now, try to apply the same algorithm to over 100 million potential targets. You may encounter all kinds of performance issues caused by the sheer volume of data.

Then there are more fundamental errors stemming from the database structure itself. What if the main database structure is different from that of the development sample? That type of discrepancy – which is very common – often leads to disasters.

Always check if anything is different between the development samples and the main database:

  • Database Structure: There are so many types of database platforms, and the way they store simple transaction data may be vastly different. In general, to rank individuals, each data record must be scored on an individual level, not transaction or event levels. It is strongly recommended that data consolidation, summarization, and variable creation be done in an analytics-friendly environment “before” any modeling begins. Structural consistency eliminates many potential errors.
  • Variable List/Names: When you have hundreds, or even thousands of variables in the database, there will be similar sounding names. I’ve seen many different variable names that may represent “Total Individual Dollar Amount Past 12-month,” for example. It is a common mistake to use a wrong data field in the scoring process.
  • Variable Values: Not all similar sounding variables have similar values in them. For example, ever-so-popular “Household Income” may include dollar values in thousand-dollar increments, or pre-coded value that looks like alphabets. What if someone changed the grouping definition of such binned variables? It would be a miracle if the model scores come out correctly.
  • Imputation Assumptions: There are many ways to treat missing values (refer to “Missing Data Can Be Meaningful”). Depending on how they were transformed and stored, even missing values can be predictable in models. If missing values are substituted with imputed values, it is absolutely important to maintain their consistency throughout the process. Mistreatment of missing values is often the main cause for scoring errors.

Mishap #4: Nature of Data Is Significantly Shifted

Data values change over time due to outside factors. For instance, if there is a major shift in the business model (e.g., business moving to a subscription model), or a significant change in data collection methods or vendors, consider that all the previous models are now rendered useless. Models should be predictors of customer behaviors, not reflections of changes in your business.

Mishap #5: Scores Are Tempered After-the-Fact

This one really breaks my heart, but it happens. I once saw a user in a major financial institution unilaterally change the ranges of model decile groups after observing significant fluctuations in model group counts. As you can imagine by now, uneven model group counts are indeed revealing serious inconsistencies caused by any of the factors that I mentioned thus far. You cannot tape over a major wound — just bite the bullet and commission a new model when you see uneven or inconsistent model decile counts.

Mishap #6: There Are Selection Errors

When campaign targets are selected based on model scores, the users must be fully aware of the nature of them. If the score is grouped into model groups 1 through 10, is the ideal target “1” or “10”?

I’ve seen cases where the campaign selection was completely off the mark, as someone sorted the raw score in an ascending order, not a descending order, pushing the worse prospects to the top. But I’ve also seen errors in documentation or judgement, as it can be really confusing to figure out which group is “better.”

I tend to put things in 0-9 scale when designing a series of personas or affinity models to avoid confusion. If score groups range from 0 to 9, the user is much less likely to assume that “zero” is the best score. Without a doubt, reversed score is far worse than not using the model at all.

Final Thoughts

After all, the model algorithm itself can be wrong, too. Not all modelers are equally competent, and machine-learning is only as good as the analyst who originally set it up. Of course, you must turn that stone when investigating bad results. But you should trace all pre- and post-modeling steps, as well. After years of such detective work, my bet is firmly on errors outside the modeling processes, unless the model validation smells fishy.

In any case, do not entirely give up on modeling just because you’ve had a few bad results. There are many things to be checked and tweaked, and model-based targeting is a long series of iterative adjustments. Be mindful that even a mediocre model is still better than someone’s gut feelings, if it is applied to campaigns properly.

Taking Omnichannel Marketing Outbound in 2020!

While a strong omnichannel customer experience is important, it’s equally important to incorporate omnichannel marketing into your lead generation strategy. Content optimization, customer modeling, and profiling through a strategic optichannel plan will produce a strong customer acquisition system.

Omnichannel marketing is an important piece of any brand’s customer experience (CX) strategy, but too often it stops there. While a strong omnichannel CX is important, it’s equally important to incorporate omnichannel marketing into your lead generation strategy. Content optimization, customer modeling, and profiling through a strategic optichannel plan will produce a strong customer acquisition system.

Here are three ways to use the power of omnichannel marketing to enhance your outbound marketing and generate leads, acquire customers, and lay the foundation for strong customer relationships.

1. Omnichannel Content Optimization

The biggest difference between omnichannel CX and omnichannel marketing is that the CX mostly happens on your owned channels, and it mostly engages existing customers and lower-funnel prospects deciding to become customers.

But how do you get those prospects into the pipeline in the first place? Traditional mass marketing? That’s not the right way to introduce prospects to a highly targeted, personalized, omnichannel experience. Maybe Disney can pull that off, but most brands need to put more effort into building a strong foundation for the customer experience.

That’s where omnichannel marketing comes in. We recently dove into how four brands deliver great omnichannel customer experiences by anticipating individual customer needs and removing obstacles that would have a negative impact on customer experience. In omnichannel marketing, you take that same approach to outbound marketing content. That can be as simple as offering a discount or as complex as creating videos to counter known buying objections.

Great omnichannel marketing comes from understanding what your target audience wants and needs, and providing content that addresses those drives. At a minimum, you must develop ad content tailored to the specific segments you’re targeting. Blasting the same offer to all of your audience models is not omnichannel marketing.

For prospects who are already pretty far down the funnel, target them with ad content that makes it easy to see that you offer the things they want and will make them easy to get.

Not all prospect segments are going to be that far down the funnel, though. You may be using omnichannel marketing to drive awareness and get top-of-funnel prospects to sign up as leads and receive your newsletter. Here, educational content can be highly effective. If they’re new to the market, promote blog content that answers common newbie questions. If they’re experienced — but not looking to buy yet — promote high-value content that makes an impression and encourages them to come to you for answers (technology companies like Cisco and HubSpot do a wonderful job of this).

Keep in mind that a targeted audience offers new opportunities to optimize content. For example,  Google affinity audiences allow advertisers to loosely target visitors of competing websites. For these kinds of campaigns, you can talk specifically about the kinds of things those websites cover.

2. Turn Customer Data From a Microscope Into a Telescope

Every brand has customer data, but even though that data lets marketers examine their customers in small — even microscopic — detail, most have a hard time using it to do much more than send birthday emails and make fairly shallow product recommendations.

In order to use your data for true outbound omnichannel marketing, you need to turn that data around so it can be your telescope instead of a microscope. You can do this by examining the data to extrapolate traits from your existing customers that also should appear on likely customers — i.e., look-a-like modeling.

The process is two-fold data science. First, you identify the segments you want to model in your customer data and look for data points they have in common. These traits may indicate someone is likely to become your customer, but it’s not a single-factor analysis. Each segment may have demographic, psychographic, and behavioral variables you can synthesize to create models that will help find other likely customers.

Then you use those models to target both online and offline marketing. For example, Facebook has long offered look-a-like targeting to its audience. Google offers similar options across its whole online and mobile ad network. You can also use these models to identify mailing lists that include the right kind of audiences and target them with relevant marketing.

Omnichannel marketing is not just for direct response, either. It is highly effective at getting the right content in front of your target audience on social media. You can use these models to target content promotion on social networks and make sure the right stories from your accounts wind up in the feeds of the right people on each network.

3. Make Omnichannel Marketing Optichannel

As mentioned, omnichannel marketing takes everything you do to build your omnichannel customer experience and applies it to lead generation and customer acquisition. You can take this further to an optichannel strategy by constricting your outreach to just the channels where each customer prefers to engage with marketing. That may sound counterintuitive as part of an omnichannel strategy, but consumers and business audiences are both showing fatigue with being hounded by ads from every brand on every channel. There are benefits to actually limiting the channels you use for specific customers by selecting ones that can be effectively optimized.

If you can identify the preferred channel of a specific audience segment — or, ideally, individual prospects — and create a great experience for them on that channel, you stand a much better chance of laying the foundation for a great omnichannel customer relationship.

Omnichannel CX has been a breakthrough for many brands. Done well, the techniques it uses can provide your customers with the kind of experiences that keep them coming back — it’s like customer relationship magic. But if you can’t take those principles and apply them to your outbound marketing as well, you’re doing a disservice to brand growth. Use these tips to turn your CX strategy around and leverage the power of true omnichannel marketing.