Do you know your customer? Bank risk assessment based on machine learning

Abstract

Know Your Customer (KYC) data can serve as a valuable risk assessment tool for banks by providing information that can identify customers who are more likely to default on a loan. This study aims to provide an accurate risk assessment tool using unique KYC data and machine-learning techniques to overcome problems in existing risk detection methods. This study proposes that the bank branch is the best level at which to determine the degree of default risk, and can also provide insight into patterns of suspicious transactions. Bank managers and regulators can focus on suspicious behavior at specific branches to increase overall compliance and reduce the risk of illegal activity.