arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.07578cs.CRcs.LGstat.ML
收藏

基于ARIMA模型的信用卡交易异常和欺诈检测

Anomaly and Fraud Detection in Credit Card Transactions Using the ARIMA Model

University of Applied Sciences and Arts, Western Switzerland (HES-SO)(瑞士西部应用科学与艺术大学);School of Engineering and Business Vaud (HEIG-Vd)(沃州工程与商业学院);NetGuardians SA(NetGuardians 公司)

Giulia Moschini, Régis Houssou, Jérôme Bovay, Stephan Robert-Nicoud

摘要:

研究了非平衡数据集上基于ARIMA模型的信用卡欺诈检测的无监督方法。ARIMA模型适用于客户的常规支出行为,如果出现一些偏差或差异,则用于检测欺诈行为。我们的模型被应用到信用卡数据集,并比较了4个异常检测方法,如K均值,箱线图,局部离群因子和隔离森林。结果表明,ARIMA模型比基准模型具有更好的检测能力。

英文摘要:

This paper addresses the problem of unsupervised approach of credit card fraud detection in unbalanced dataset using the ARIMA model. The ARIMA model is fitted on the regular spending behaviour of the customer and is used to detect fraud if some deviations or discrepancies appear. Our model is applied to credit card datasets and is compared to 4 anomaly detection approaches such as K-Means, Box-Plot, Local Outlier Factor and Isolation Forest. The results show that the ARIMA model presents a better detecting power than the benchmark models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑