Integrate Skill Sets With Data Mining Techniques
Such a team generally consists of direct marketers, creative professionals and data miners. The data miners, with a quantitative focus, must be versed in many quantitative techniques such as predictive models, clusters, demographic profiles and focus group and survey research. They must understand how to combine these techniques into a robust foundation for sophisticated targeting.
Few catalogers have successfully blended multiple skill sets and data mining techniques into a targeting program. This article will give a blueprint for doing so.
Predictive models. A statistics-based predictive model is a mathematical equation that ranks individuals from most to least attractive future predicted behavior. Generally, this rank is divided into equal groups of similarly performing individuals.
A predictive model generates segments containing individuals with no common guaranteed characteristics beyond future predicted behavior. Customers within a given segment might be a combination of young and old, males and females. They might display many patterns of historical merchandise purchase behavior.
With a predictive model, all database fields with the potential to isolate the "goods" from the "bads" are systematically evaluated. The model itself easily can be implemented into a production environment. All customers above a predetermined predicted performance are promoted. Therefore, models are an advanced way to help determine whom to promote.
Sophisticated targeting, however, also requires insight into what to promote. This is where the techniques of clusters, demographic profiles and focus group and survey research come into play.
Clusters. Unlike predictive models, clusters provide segment homogeneity. By definition, segment homogeneity exists when a group of individuals has at least one thing in common. Examples are life stage, merchandise category needs or permutations of both.
Segment homogeneity is a prerequisite for one-to-few marketing. One-to-few marketing, unlike one-to-one, is almost always cost-effective.
Consider a form of clustering called product affinity analysis, in which groups of customers are defined by their merchandise purchase patterns within and across orders. Assume that six product affinity clusters are created, and that a given customer has purchased just once - a single item within Cluster #1. Ad hoc efforts can be made to sell other items within Cluster #1, such as:
· Web recommendation agents, at the time of purchase, when the medium of purchase is the e-commerce site.
· E-mail microtargeting, subsequent to the purchase.
· Ink-jet messaging, subsequent to the purchase, with a catalog cover callout involving one or more of the Cluster #1 pages.
· Interactive call center efforts at the time of the purchase or during subsequent contacts.
· Layout fine-tuning, subsequent to the purchase, for print media and the e-commerce site. This allows positioning of merchandise to be adjusted to reflect typical purchase patterns.
· Formal specialized predictive models can be implemented, such as:
· Affinity group models to rank Cluster #1 buyers by future predicted purchase volumes across Cluster #1 merchandise.
· Cross-sell models to rank non-Cluster #1 buyers based on their likelihood of eventually buying Cluster #1 merchandise. This most often is done with high-value clusters to drive prospecting efforts within the customer base.
Affinity group and cross-sell models can drive focused initiatives such as merchandise-specific special offers, including e-mail. They also can spearhead selective binding involving supplemental signatures of Cluster #1 merchandise.
Focus group and survey research. Unlike predictive models, focus group and survey research provides attitudinal insight. But many catalogers do not systematically employ such research.
A specialty cataloger replaced RFM cells with a statistics-based predictive model. As a result, wasteful circulation was eliminated and the promotional savings were reinvested in sophisticated targeting programs.
On average, males were half as responsive as females. Using clustering techniques, a subset of very responsive males was identified: those who had bought female-oriented jewelry. However, by analyzing the database itself, there was no way to determine who in the household was driving the activity. It could, for example, have been daughters using the father's credit cards.
Subsequently, this customer subset of responsive males was overlaid with demographic information such as age, income, marital status and presence of children. Results indicated that these jewelry-buying households were families with children, living in single-family suburban homes, with professional, technical and managerial occupations.
Knowing that the target audience was married suburbanites rather than single city-dwellers helped tailor the catalog copy and layout. Yet it provided no insight into the individual within the household who was driving the jewelry purchases. To gain a definitive answer, focus group and survey research was commissioned.
The research indicated that most of these individuals were gift-giving husbands. They were what the research company dubbed "unimaginative male gift givers." These were men who, despite their professional success, dreaded buying birthday, anniversary and holiday gifts for their spouses. They were at a loss for the types of presents their wives might find appealing.
To leverage these findings, a task force was convened. Comprised of representatives from marketing, creative and analytics, the mandate was to develop a loyalty program to appeal to these "unimaginative male gift givers."
On the prospecting side, the cataloger's circulation department began working with its list broker to identify male-oriented lists for which to target prospect offers. These offers included a description of the loyalty program as well as a form for signing up.
Over time, the cataloger extended aggressively into a new and different target market. Its top and bottom lines were enhanced because of the combination of multiple skill sets and data mining techniques.