Applications of machine learning : consumer credit risk analysis

Abstract

Current credit bureau analytics, such as credit scores, are based on slowly varying consumer characteristics, and thus, they are not adaptable to changes in customers behaviors and market conditions over time. In this paper, we would like to apply machine-learning techniques to construct forecasting models of consumer credit risk. By aggregating credit accounts, credit bureau, and customer data given to us from a major commercial bank (which we will call the Bank, as per confidentiality agreement), we expect to be able to construct out-of-sample forecasts. The resulting models would be able to tackle common challenges faced by chief risk officers and policymakers, such as deciding when and how much to cut individuals account credit lines, evaluating the credit score for current and prospective customers, and forecasting aggregate consumer credit defaults and delinquencies for the purpose of enterprise-wide and macroprudential risk management.