Credit Risk Analysis Using Machine and Deep Learning Models

Dominique Guegan (1, 2, 3, 4, 5) , Peter Martey Addo (6, 3) , Bertrand Hassani (3, 2, 7, 8)

1 UP1 - Université Paris 1 Panthéon-Sorbonne
2 CES - Centre d'économie de la Sorbonne
3 Labex ReFi
4 IPAG Business School
5 University of Ca’ Foscari [Venice, Italy]
6 AFD - Agence française de développement
7 Capgemini Consulting [Paris]
8 UCL-CS - Department of Computer science [University College of London]

Due to the advanced technology associated with Big Data, data availability and computing power, most banks or lending institutions are renewing their business models. Credit risk predictions, monitoring, model reliability and effective loan processing are key to decision-making and transparency. In this work, we build binary classifiers based on machine and deep learning models on real data in predicting loan default probability. The top 10 important features from these models are selected and then used in the modeling process to test the stability of binary classifiers by comparing their performance on separate data. We observe that the tree-based models are more stable than the models based on multilayer artificial neural networks. This opens several questions relative to the intensive use of deep learning systems in enterprises.

Mots clés: financial regulation; deep learning; Big data; data science; credit risk

Domaines: Economies et finances; Méthodes et statistiques

Dominique Guegan, Peter Martey Addo, Bertrand Hassani. Credit Risk Analysis Using Machine and Deep Learning Models. Risks, 2018, Computational Methods for Risk Management in Economics and Finance, 6 (2), pp.38. ⟨10.3390/risks6020038⟩. ⟨halshs-01835164⟩