How training on multiple time slices improves performance in churn prediction

DOI10.1016/j.ejor.2021.05.035zbMath1487.90409OpenAlexW3167284347MaRDI QIDQ2239912

Theresa Gattermann-Itschert, Ulrich Wilhelm Thonemann

Publication date: 5 November 2021

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

Full work available at URL: https://doi.org/10.1016/j.ejor.2021.05.035

zbMATH Keywords

marketingretailingmachine learninganalyticschurn prediction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Marketing, advertising (90B60)

Related Items (2)

Predicting customer churn: A systematic literature review ⋮ Reconciling business analytics with graphically initialized subspace clustering for optimal nonlinear pricing

Uses Software

• SMOTE

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees
• CRM in social media: predicting increases in Facebook usage frequency
• Customer base analysis: partial defection of behaviourally loyal clients in a non-contractual FMCG retail setting
• Modeling churn using customer lifetime value
• A reference model for customer-centric data mining with support vector machines
• Wrappers for feature subset selection
• A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data
• Quantitative models for direct marketing: A review from systems perspective
• Random forests
• Gene selection for cancer classification using support vector machines

This page was built for publication: How training on multiple time slices improves performance in churn prediction