Artificial intelligence credit risk prediction: An empirical study of analytical artificial intelligence tools for credit risk prediction in a digital era

Abstract

Global consumer lending has seen a compound annual growth rate (CAGR) of 4.8 per cent forecasted to 2020. The financial system is once again at risk; it is a decade since the credit crunch, yet the causes have not been solved; however, globally, the outstanding amount of credit doubled compared to the lending volume of 2008. Also, increasingly more credit decisions are being taken today. Furthermore, millennials’ service expectations drive transformation from traditional lending into digital lending. The CAGR for digital lending is 53 per cent 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 and the stability of the global financial system. This paper contains research from across the UK and the Netherlands: two advanced lending markets, selected because of their advancements in digital lending, to examine to what extent lenders can advance their credit decisions with individual risk assessments with artificial intelligence (AI). The research has applied supervised learning and has been performed on 133,152 mortgage and credit card customers in prime, near prime and sub-prime lending segments of three European lenders across the UK and the Netherlands during the period January 2016 to July 2017. As candidate models, we chose neural nets and random forests, as they are the most popular supervised learning methods in credit risk for their benefit of applying both structured and unstructured data. The research describes three experiments that develop the AI probability of default models and compares the model quality with the quality of the traditional applied logistic probability of default (PD) 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.