Improving features selection for customer churn prediction using Whale Optimization Algorithm

With the growing competition between organizations, customer retention and especially customer churn prediction is one of the most important issues in customer relationship management. Churn prediction is one of the most popular Big Data use cases in business environment. It is always more difficult and expensive to acquire a new customer than it is to retain a current paying one. Set of wide range data related to daily operations collected by automation operations flows, provides suitable platform for exploitation of data mining techniques. Term of customer churn prediction usually evaluated in classification area by dividing customers in two classes, namely customers whom leaving organization and the loyal ones. Churn prediction modeling techniques attempt to understand the precise customer behaviors and attributes which signal the risk and timing of customer churn. The accuracy of the technique used is obviously critical to the success of any proactive retention efforts. The important part of churn prediction is selecting subset of features. In this paper, we discuss the latest optimization algorithm named Whale Optimization Algorithm (WOA) for subset feature selection problem. WOA is a recently developed swarm-based optimization algorithm inspired by the hunting behavior of humpback whales. WOA has a fast convergence rate due to the use of roulette wheel selection method for subset feature selection compared with GA, PSO and other well-known techniques that confirm the effectiveness of this algorithm.

Keywords:

Customer churn prediction , feature selection optimization , Whale optimization algorithm