Auto loan fraud detection using dominance-based rough set approach versus machine learning methods
作者：
Highlights：
• Real data concerning auto loan applications are analyzed to discover fraud patterns.
• Dominance-based Rough Set Balanced Rule Ensemble outperforms Random Forest and SVM.
• Proposed approach directly addresses the problem of class imbalance.
• Induced decision rules reveal human-understandable patterns of auto loan frauds.
• Interpretable results of the proposed approach enable insight into auto loan frauds.
摘要
•Real data concerning auto loan applications are analyzed to discover fraud patterns.•Dominance-based Rough Set Balanced Rule Ensemble outperforms Random Forest and SVM.•Proposed approach directly addresses the problem of class imbalance.•Induced decision rules reveal human-understandable patterns of auto loan frauds.•Interpretable results of the proposed approach enable insight into auto loan frauds.
论文关键词：Fraud detection,Auto loan,Dominance-based Rough Set Balanced Rule Ensemble,Decision rules,Random Forest,SVM
论文评审过程：Received 16 January 2020, Revised 30 June 2020, Accepted 9 July 2020, Available online 25 July 2020, Version of Record 6 August 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113740
