Feature engineering strategies for credit card fraud detection

作者：

Highlights：

• Credit card fraud detection evaluation measure.

• Each example is assumed to have different financial cost.

• Transaction aggregation strategy for predicting fraud.

• Periodic features using the von Mises distribution.

• Code is open source and available at albahnsen.com/CostSensitiveClassification.

摘要

•Credit card fraud detection evaluation measure.•Each example is assumed to have different financial cost.•Transaction aggregation strategy for predicting fraud.•Periodic features using the von Mises distribution.•Code is open source and available at albahnsen.com/CostSensitiveClassification.

论文关键词：Cost-sensitive learning,Fraud detection,Preprocessing,Von Mises distribution

论文评审过程：Received 26 July 2015, Revised 4 December 2015, Accepted 21 December 2015, Available online 7 January 2016, Version of Record 22 January 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.12.030