A FUZZY MATHEMATICAL PROGRAMMING APPROACH FOR CROSS-SELL OPTIMIZATION IN RETAIL BANKING

摘要

In this paper we discuss the mailer selection problem in retail banking. Mailer selection takes estimates of several parameters (like response probability of a customer, expected volume, expected profit from a customer etc.) and decides on the list of customers to whom the offer should be sent such that a certain set of business objectives are met/optimized. We discuss some of the issues (unreliable estimates and computational complexity) related to the mailer selection process and propose solution to the problems. We propose a fuzzy mathematical programming technique to take care of the imprecise estimates of the parameters. The imprecise parameters and constraints are represented as triangular fuzzy numbers. We use a simple example to demonstrate the method.