Profit driven decision trees for churn prediction

DOI10.1016/J.EJOR.2018.11.072zbMATH Open1441.62739arXiv1712.08101OpenAlexW2963345615WikidataQ128846197 ScholiaQ128846197MaRDI QIDQ2178124FDOQ2178124

Authors: Sebastiaan Höppner, Eugen Stripling, Bart Baesens, Seppe vanden Broucke, Tim Verdonck 

Publication date: 7 May 2020

Published in: European Journal of Operational Research (Search for Journal in Brave)

Abstract: Customer retention campaigns increasingly rely on predictive models to detect potential churners in a vast customer base. From the perspective of machine learning, the task of predicting customer churn can be presented as a binary classification problem. Using data on historic behavior, classification algorithms are built with the purpose of accurately predicting the probability of a customer defecting. The predictive churn models are then commonly selected based on accuracy related performance measures such as the area under the ROC curve (AUC). However, these models are often not well aligned with the core business requirement of profit maximization, in the sense that, the models fail to take into account not only misclassification costs, but also the benefits originating from a correct classification. Therefore, the aim is to construct churn prediction models that are profitable and preferably interpretable too. The recently developed expected maximum profit measure for customer churn (EMPC) has been proposed in order to select the most profitable churn model. We present a new classifier that integrates the EMPC metric directly into the model construction. Our technique, called ProfTree, uses an evolutionary algorithm for learning profit driven decision trees. In a benchmark study with real-life data sets from various telecommunication service providers, we show that ProfTree achieves significant profit improvements compared to classic accuracy driven tree-based methods.

Full work available at URL: https://arxiv.org/abs/1712.08101

Recommendations

• Profit-based churn prediction based on minimax probability machines
• ADtreesLogit model for customer churn prediction
• Churn detection via customer profile modelling
• Customer churn predictive modeling by classification methods
• A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees

zbMATH Keywords

classificationcustomer churn predictionevolutionary algorithmartificial intelligenceprofit-based model evaluation

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to economics (62P20) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Development and application of consumer credit scoring models using profit-based classification measures
• Title not available (Why is that?)
• Random forests
• Statistical comparisons of classifiers over multiple data sets
• Title not available (Why is that?)
• Modeling churn using customer lifetime value
• Measuring classifier performance: a coherent alternative to the area under the ROC curve
• A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data
• Title not available (Why is that?)
• Constructing optimal binary decision trees is NP-complete
• The asymptotic theory of permutation statistics.
• Improved customer choice predictions using ensemble methods
• An approach to a problem in network design using genetic algorithms
• Introduction to evolutionary computing

Cited In (12)

• Explainable AI for operational research: a defining framework, methods, applications, and a research agenda
• Modeling churn using customer lifetime value
• Instance-dependent cost-sensitive learning for detecting transfer fraud
• Mathematical optimization in classification and regression trees
• Predicting customer churn: A systematic literature review
• ADtreesLogit model for customer churn prediction
• Churn detection via customer profile modelling
• Automated cellular modeling and prediction on a large scale
• Reconciling business analytics with graphically initialized subspace clustering for optimal nonlinear pricing
• B2Boost: instance-dependent profit-driven modelling of B2B churn
• EFFECT OF THE COMPANY RELATIONSHIP NETWORK ON DEFAULT PREDICTION: EVIDENCE FROM CHINESE LISTED COMPANIES
• Profit-based churn prediction based on minimax probability machines

Uses Software

• UCI-ml
• evtree

This page was built for publication: Profit driven decision trees for churn prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2178124)