Sequence classification for credit-card fraud detection

作者：

Highlights：

• Comparison of sequence learner and static learner on real-world dataset.

• Sequence learner improves fraud detection on offline transactions.

• Both sequence learner and static learner benefit from manual feature aggregations.

• Frauds detected by sequence learner and static learner are consistently different.

摘要

•Comparison of sequence learner and static learner on real-world dataset.•Sequence learner improves fraud detection on offline transactions.•Both sequence learner and static learner benefit from manual feature aggregations.•Frauds detected by sequence learner and static learner are consistently different.

论文关键词：Finance,Credit-card fraud detection,Sequence classification,Long short-term memory networks

论文评审过程：Received 12 September 2017, Revised 2 January 2018, Accepted 23 January 2018, Available online 31 January 2018, Version of Record 16 February 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.01.037