Wednesday, 16 November 2011

Value at Risk segmentation and retention campaigns

In Propensity Based Segmentation customers are grouped according to propensity scores, such as churn scores, cross selling scores etc., as estimated by respective classification (propensity) models. Propensity scores can also be combined with other segmentation schemes to better target marketing actions. The Value at Risk segmentation scheme is developed by combining propensities with Value Segments to prioritize retention actions. 

Churn models estimate the churn propensity for each customer, indicating the likelihood of churn. Through simple computations and binning, customers can then be assigned to distinct groups based on their churn score. For instance, appropriate cut-off values can be selected and customers can be divided into groups of low, medium and high churn likelihood as a result of a churn model. 

When value segments are cross-examined with churn propensity segments we have the Value at Risk segmentation, a compound segmentation which can be used for prioritizing retention campaigns. An example of this segmentation is shown in the following figure. 

Six compound segments are created after combining the Low-Medium-High value segments with the Low-Medium-High risk segments (the segments of Low and Medium value segments are collapsed to final segments 5 and 6).


Clearly, segment 1 the most critical one as it contains high value customers with increased risk of terminating their relation with the organization. For this segment retention is a first priority.

No comments: