Exceptional results.
What Direct Marketers Need To Know About Segmentation
Part 2 of a Multi-Part Series
By David Shepard
These four articles first appeared in Direct Magazine
In our last article we defined the objective of a survey developed, attitudinal segmentation scheme that would separate our hypothetical chain store customers in to four clusters based on the following set of major dimensions: (1) price, (2) service (3) product depth (4) product quality (5) the overall shopping experience and (6) brand image, and asked the question: how would we go about doing it?
If we follow the traditional path we would probably hire a market research company to develop an “in-depth” questionnaire that would be presented to a random sample of a few thousand of our customers. (In the home or through direct mail, maybe even over the phone.)
The results of the survey would be processed and for sure the research firm will identify four or five major segments, let’s call them:
1. The bargain hunters -- 30% of the sample
- They only buy “on deal” never pay full price, not terribly concerned with quality.
2. The quality seekers – 30% of the sample
- They’ll pay full price if they think the quality is there and they’ll spend a long time looking for the right combination of price and quality.
3. The convenience shoppers -- 25% of the sample
- They’re pressed for time, buy only what they came looking for, are not price conscious, they hate to shop.
4. The old timers – 15% of the sample
- They’ve been shopping with you for years and can’t remember why.
Now, let’s assume that we buy into the results of the segmentation -- that is, that we believe that our customer file probably does break down into these four segments and in proportions fairly close to those shown above.
How do we go about placing all of our customers into the right segment? Remember, the segmentation was based on just a sample of our customers, and it’s not practical or economically feasible to send the same questionnaire to all of our customers.
The answer has to be through predictive modeling. We need to be able to predict which segment a customer is most likely to belong to. The question is -- how likely are we to succeed? To answer this question we have to consider the data we have about both those that answered the survey and all of our customers that need to be scored and placed into segments.
The data both groups have in common is behavior/transaction data and/or demographics. Thus the question now becomes the following: are the attitudes reflected in our segmentation likely to be correlated with the available behavioral and demographic data?
My guess is that in this case the answer may be yes, not perfectly of course, but sufficiently correlated so that we can come reasonable close to the results we would have gotten if the entire database of customers was surveyed.
Let’s look at what we have to work with.
Segment 1. The Bargain Hunters should be identifiable on the basis of the prices they paid for the items purchased—assuming the database could yield this information.
Segment 2. The Quality Seekers should also be identifiable by examining the products purchased and the prices paid – here however a lot of additional analysis and coding will probably be required if “quality” is not easily identified from data maintained on the database.
Segment 3. The Convenience Shoppers might be identified by gender, they sound male to me, and by their shopping patterns, probably relatively few items purchased on the same day.
Segment 4. The Old Timers may display a relatively constant purchase behavior over a relatively long period of time, and they may be chronologically older, as well as being on the file longer.
So, in this hypothetical case we have a segmentation scheme that seems to make sense, in that it conforms to our understanding of our business; and we have a segmentation that should be reasonably predictable through modeling because the attitudes discovered would seem to be correlated with the information contained in our database.
This might not always be the case. It may be that the segmentation though correct, may yield segments that are not correlated with available behavior or demographic data. For example, in financial services, an important attitudinal distinction exists between investors that like to do their own research and make their own decisions, and those that want someone else to do the hard work. But this distinction may not be correlated to any known demographic or any behavioral information kept on the database.
In these situations it may be appropriate to first build a segmentation model based on demographic and behavioral data and then research the segments. And, as discussed above, within this framework there are numerous options. For example one could segment first just using demographics and then once you have these demographic segments use behavior data to divide the demographic segments into “high value” and “low value” customers. Then bases on these two dimensional segments one could use research to understand the differences in behavior; or one could combine demographic data with behavior data create a similar number of segments and then research those segments.
So, it’s fair to ask, if a segmentation based on survey data may or may not be projectable to the entire universe should it or should it not be done?
One answer is to do it and see what happens. Not a very good answer.
Another answer is to do some limited research and a quick and dirty segmentation, before rolling out the full survey and test to see if the segmentation appears to be projectable, at least projectable enough to be used.
Table 1 below shows the results of what would have been a very successful prediction with 82% of the names modeled falling into the correct segment. In table 2 the correct classification is only 52%. Directionally correct by not nearly as accurate, and the kind of result likely to get a direct marketer into trouble.
Table 1
|
Table 2
|
Trouble comes about in the following way. Using the results shown in Table 2 we’re right in our placement about 50% of the time…much better than the chance rate of 26% (see the footnote for the calculation).
But that means were also wrong about 50% of the time. Now if our creative team develops packages for each segment that are very targeted -- by that we mean packages that are perfectly appropriate for members of the segment when the prediction is correct, but not appropriate for misplaced members -- they could possibly reduce response among these incorrectly placed customers by more than they increase response among the correctly assigned customers.
Now, when we test these targeted packages against a non-targeted control package (one that appeals somewhat to all segments and turns off none) it’s not unusual to see the general control beating the targeted packages.
Does this mean that we shouldn’t be doing segmentation, attitudinal or otherwise…of course not? But it does mean that we have to proceed carefully.
How? Come back in April and we’ll answer this question and begin our in-depth look at the tools of segmentation: factor and cluster analysis.
continue to: What Direct Marketers Need To Know About Segmentation Part 3