This website requires JavaScript.

Machine Learning in Transaction Monitoring: The Prospect of xAI

Julie GerlingsIoanna Constantiou
Oct 2022
摘要
Banks hold a societal responsibility and regulatory requirements to mitigatethe risk of financial crimes. Risk mitigation primarily happens throughmonitoring customer activity through Transaction Monitoring (TM). Recently,Machine Learning (ML) has been proposed to identify suspicious customerbehavior, which raises complex socio-technical implications around trust andexplainability of ML models and their outputs. However, little research isavailable due to its sensitivity. We aim to fill this gap by presentingempirical research exploring how ML supported automation and augmentationaffects the TM process and stakeholders' requirements for building eXplainableArtificial Intelligence (xAI). Our study finds that xAI requirements depend onthe liable party in the TM process which changes depending on augmentation orautomation of TM. Context-relatable explanations can provide much-neededsupport for auditing and may diminish bias in the investigator's judgement.These results suggest a use case-specific approach for xAI to adequately fosterthe adoption of ML in TM.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答