arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.07508cs.LG
收藏

基于图的机器学习反洗钱预警优化

Anti-Money Laundering Alert Optimization Using Machine Learning with Graphs

Feedzai;University of Porto(波尔图大学)

Ahmad Naser Eddin, Jacopo Bono, David Aparício, David Polido, João Tiago Ascensão, Pedro Bizarro, Pedro Ribeiro

摘要:

洗钱是一个全球性的问题,涉及使毒品交易、人口贩运或腐败等严重重罪(每年1.7-4万亿欧元)的收益合法化。金融机构部署的反洗钱系统通常包括与监管框架相一致的规则。人类调查人员审查警报并报告可疑情况。这类系统的误报率很高,影响了系统的有效性,并导致高昂的运营成本。我们提出了一个机器学习分类模型,它补充了基于规则的系统,并学会准确预测警报的风险。我们的模型同时使用以实体为中心的工程特征和以基于图形的特征的形式表征实体间关系的属性。我们利用时间窗口来构建动态图,优化时间和空间效率。我们在真实世界的银行数据集上验证了我们的模型,并展示了分类模型如何将误报数量减少80%,同时检测到超过90%的真阳性。通过这种方式,我们的模型可以显著改善反洗钱业务。

英文摘要:

Money laundering is a global problem that concerns legitimizing proceeds from serious felonies (1.7-4 trillion euros annually) such as drug dealing, human trafficking, or corruption. The anti-money laundering systems deployed by financial institutions typically comprise rules aligned with regulatory frameworks. Human investigators review the alerts and report suspicious cases. Such systems suffer from high false-positive rates, undermining their effectiveness and resulting in high operational costs. We propose a machine learning triage model, which complements the rule-based system and learns to predict the risk of an alert accurately. Our model uses both entity-centric engineered features and attributes characterizing inter-entity relations in the form of graph-based features. We leverage time windows to construct the dynamic graph, optimizing for time and space efficiency. We validate our model on a real-world banking dataset and show how the triage model can reduce the number of false positives by 80% while detecting over 90% of true positives. In this way, our model can significantly improve anti-money laundering operations.

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。

↑