Machine learning: A revolution in risk management and compliance?

Financial institutions (FIs) are increasingly looking to deploy machine learning approaches to manage and mine regulatory reporting data and unstructured information. This article aims to introduce the machine learning field and discusses several "regtech" application cases within FIs, based on discussions with the sector and with technology ventures: credit risk modeling, detection of credit card fraud and money laundering, and surveillance of conduct breaches. Two tentative conclusions emerge on the added value of applying machine learning in the financial services sector. First, the ability of machine learning methods to analyze very large amounts of data, while offering a high granularity and depth of predictive analysis, can significantly improve analytical capabilities across risk management and compliance areas, such as money laundering detection and credit risk modeling. Second, the application of machine learning approaches within the financial services sector is highly context-dependent. Data quality and availability can be an issue; more importantly, the predictive performance and granularity of analysis of several approaches can come at the cost of increased model complexity and a lack of explanatory insight. This is an issue particularly where analytics are applied in a regulatory context, and a supervisor or compliance team will want to audit and understand the applied model.