Explainable AI in Fintech Risk Management

• DOI: 10.3389/frai.2020.00026
• Publication Date: 2020-05-11T09:37:20Z
• Authors: Niklas Bussmann; Paolo Giudici; Dimitri Marinelli; Jochen Papenbrock
• Keywords: Credit score

The paper proposes an explainable AI model that can be used in credit risk management and, particular, measuring the risks arise when is borrowed employing scoring platforms. applies similarity networks to Shapley values, so predictions are grouped according underlying explanatory variables. empirical analysis of 15,000 small and medium companies asking for reveals both risky not borrowers a set similar financial characteristics, which employed explain understand their score therefore, predict future behaviour.