An Effective Approach for Implementation
Database analysts often encounter data on individuals for whom a missing profit (back-end) value is recorded as a consequence of their non-approval, although they have positive responses (front-end) to a solicitation. Among the individuals who do respond, there is a wide variation in the profit values. The literature on the estimation of a regression model based on these missing “censored” data is extensive. Ergo, the modeling of the response-approval data is in place and easy. But, the standard implementation of the model results is unreliable, as the approach is to first create a hundred-cell table, defined by crossing the ten response deciles by the ten profit deciles. Then, the analyst “cherry-picks” the best response-approval cells among the hundred cells to target. These cells are ill-chosen by virtue of cherry-picking itself. In this article, I present an easy and reliable approach to select the best response-approval cells for target marketing.
1 800 DM STAT-1, or e-mail at firstname.lastname@example.org.