A comparison between DSS and ML models for churn prediction

Boris Delibašić, Sandro Radovanović, Marko Bohanec, Milija Suknović
May, 2025
Cite Project Source Document

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 are a technology from the 1960s that was predominantly overruled by machine learning 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.

Type
Conference paper
Publication
In Proceedings of the 11th International Conference on Decision Support System Technology - ICDSST 2025
Churn prediction Decision Support Systems DEX DIDEX Decision tree Machine Learning
Sandro Radovanović
Sandro Radovanović
Assistant Professor at University of Belgrade

My research interests include machine learning, development and design of decision support systems, decision theory, and fairness and justice concepts in algorithmic decision making.