Artificial Intelligent Credit Risk Prediction: An Empirical Study of Analytical Artificial Intelligence Tools for Credit Risk Prediction in a Digital Era

Abstract

Millennials service expectations drive transformation from traditional lending into digital lending. The CAGR for digital lending is 53% until 2025. Therefore, in this growing information age new methods for credit risk scoring could form the central pillar for the continuity of a financial institution. This paper contains the first research into AI application in individual risk assessment across two advanced lending markets. The research has been performed on 133.152 mortgage and credit card customers of 3 European lenders during the period January 2016 – July 2017. As candidate models, we chose neural nets and random forests. The research describes three experiments that develop the artificial intelligent probability of default models. In all experiments AI models performed better than the traditional models. Scalable automated credit risk solutions can therefore build on AI in their risk scoring.