Nos derniers articles

#financialinstitutions are increasingly using #machinelearningalgorithms for credit risk mgmt., #fraudprevention, and #aml. This paper presents robust evidence of using logistic regression, linear discriminant analysis, and neural networks for accurately predicting and classifying financial transactions for Volcker Rule #compliance. It provides a scalable minimum viable product to automate #controls testing.

This paper discusses the efficiency, effectiveness, and costs of #denmark's #antimoneylaundering (#aml) #compliance standards. Although the country has caught up with international standards, the current global AML compliance system is ineffective in deterring #moneylaundering by professional actors. The system imposes significant costs on #banks and society, while spending too much time on minor infractions. To improve the system, the author argues for a #risk-based approach that automates large portions of the compliance process and allows compliance staff to focus on investigations.

"... the paper surveys the obvious but seldom commented-upon facts that the vast majority of dirty money and assets resides in, passes through, or is facilitated by the world's largest and richest countries. How then do the world's main AML risk rankings invariably centre blame upon small, relatively poor, and nonwhite jurisdictions?"