A comparison between DSS and ML models for churn prediction

Abstract

This paper compares the accuracy and convenience of a classical machine learning algorithm, a decision tree, and a classical decision support system model, built by the DEX (Decision EXpert) multicriteria decision modelling method for categorical data, on a churn prediction data set. Decision support systems (DSS) are a technology from the 1960s that was predominantly overruled by machine learning (ML) in the 2010s due to the explosion of big data, and their cost effectiveness. Here we discuss the similar and different aspects of the two technologies, and demonstrate the performance of these different, yet intertwined technologies. We show that our proposed DSS model outperforms the ML model.