Customer churn prediction for an insurance company

Abstract

The objective of every company is to remain profitable and to lead the respective industry. This is achieved by attempting to attract new customers and keeping the existing ones. The problem of customer churn poses various types of challenges to a company, depending on the industry in which the company operates. In the insurance industry, the repercussions of customer churn may signify that a customer is lost for several years. Retaining customers in the insurance industry who have purchased a motor policy is even a more challenging issue since the policy is renewed every year and the policy holder could easily switch to another competitor if he is not satisfied with the service. Moreover, by Maltese law, Third Party Only (TPO) policy is minimum obligatory cover for every vehicle and thus the competition is quite high in this industry. The objective of this study was to implement a model to predict those policyholders at risk of switching to another competitor and to determine when this event is most commonly to occur. This analysis was applied to the insurance industry though the approach could be used for any other industry. Various data mining techniques, namely, Decision Trees, Logistic Regression, Naive Bayes, Neural Networks, Random Forest and Support Vector Machine SVM were used in order to predict those customers who are likely to terminate their policies. Random Forest turned out to be the best model for forecasting customer behaviour. Even the techniques, Support Machine Vectors and Decision Trees turned out to be powerful techniques to predict customer churn, reaching not only sufficient accuracy but also require less computational effort to train the model than the other techniques. In addition, apart from predicting whether a customer will renew the policy or not, using these data mining techniques, in this research, survival analysis was used to model time till the event of churn and to establish whether certain characteristics lead to churn more than others. It was concluded that approximately 90% of the policy holders survive the first five years while the majority of the policy holders do not terminate the policy before the expiry date. In addition, it was established that the number of other motor policies are associated with a decreased risk of churn while TPO covers are associated with an increased risk of churn. These identified customers who are at high risk of leaving the company could thus be targeted in marketing campaigns aimed at reducing the rate of churn and as a result increasing profitability.