Wednesday, 29 December 2010

What if there isn’t an explicit target field in propensity modeling?

In some cases there isn’t an apparent target field to predict in propensity modeling. For example, in the case of prepaid customers in mobile telephony, there isn’t a recorded disconnection event to be modelled. The separation between active and churned customers is not evident. In such cases a target event could be defined in respect to a specific customer behaviour. This handling requires careful data exploration and co-operation between the data miners and the marketers. For instance, prepaid customers with no incoming or outgoing phone usage within a certain time period could be considered as churners. 

In a similar manner, certain behaviours or changes in behaviour, for instance substantial decrease in usage or a long period of inactivity, could be identified as signals of specific events and then be used for the definition of the respective target. More over the same approach could also be followed when analysts want to act proactively. For instance, even when a churn / disconnection event could be directly identified through a customer’s action, a proactive approach would analyze and model customers before their formal attrition, trying to identify early signals of defection and not waiting for the official termination of their relationship with the customer.

Source: Data Mining Techniques in CRM. Inside Customer Segmentation, Wiley 2009

1 comment:

Mike Wills said...

Get all your data within given deadline on affordable and discounted rates on new year ocassion.
For more details visit : Http://www.jbgrab.com