Customer churning prediction using support vector machines in online auto insurance service

Abstract

Support vector machines (SVMs) are promising methods for the prediction of online auto insurance customer churning because SVMs use a risk minimization principal that consists of the empirical error and the regularized term predicting the switching probability of an insured to other auto insurance company. In addition, this study examines the feasibility of applying SVM in online insurance customer churning by comparing it with other methods such as artificial neural network (ANN) and logit model. This study proves that SVM provides a promising alternative to predict customer churning in auto-insurance service.