Cost-sensitive payment card fraud detection based on dynamic random forest and k-nearest neighbors
作者：
Highlights：
• We use dynamic random forest algorithm for the first time in fraud detection problem.
• A new similarity measure is established on the basis of transaction time.
• Transaction aggregation strategy is used to derive additional transactional features.
• Minimum risk model is applied in cost-sensitive detection.
• The results are compared with two other models.
摘要
•We use dynamic random forest algorithm for the first time in fraud detection problem.•A new similarity measure is established on the basis of transaction time.•Transaction aggregation strategy is used to derive additional transactional features.•Minimum risk model is applied in cost-sensitive detection.•The results are compared with two other models.
论文关键词：Payment card fraud detection,Dynamic random forest,Cost-sensitive detection,Minimum risk
论文评审过程：Received 15 November 2017, Revised 4 May 2018, Accepted 3 June 2018, Available online 6 June 2018, Version of Record 18 June 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.06.011
