Explainable models of credit losses

DOI10.1016/J.EJOR.2021.11.009zbMath1506.91173OpenAlexW3212268569MaRDI QIDQ2140185

Sara M. Matos, João A. Bastos

Publication date: 20 May 2022

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://rem.rc.iseg.ulisboa.pt/wps/pdf/REM_WP_0161_2021.pdf

zbMATH Keywords

forecastingrisk managementrecovery ratesloss given defaultexplainable machine learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Credit risk (91G40)

Uses Software

• XGBoost
• shap

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Greedy function approximation: A gradient boosting machine.
• Bagging predictors
• Fuzzy decision fusion approach for loss-given-default modeling
• Support vector regression for loss given default modelling
• Intertemporal Forecasts of Defaulted Bond Recoveries and Portfolio Losses*
• Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models
• Learning representations by back-propagating errors
• Random forests

This page was built for publication: Explainable models of credit losses