Determinants of non-performing loans: an explainable ensemble and deep neural network approach.

Chioma Nwafor, Obumneme Nwafor

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)
258 Downloads (Pure)

Abstract

Ensemble algorithms can learn complex nonlinear relationships in large datasets resulting in higher predictive accuracies than the conventional methods. Practitioners and regulators have shown substantial hesitance in adopting them in credit risk management because of their need for explainablity. Using five ensemble learning techniques and a one-dimensional convolutional neural network, we assess indicators to predict asset quality deterioration in a consumer loan dataset using the SHAP framework to achieve explainablity of the models' ranking of features significance. We implemented a novel model-agnostic aggregate ranking method to rank the importance of the overall features from each model in predicting NPLs.
Original languageEnglish
Article number104084
JournalFinance Research Letters
Volume56
Early online date10 Jun 2023
DOIs
Publication statusPublished - Sept 2023

Keywords

  • Credit risk
  • Ensemble methods
  • Explainable artificial intelligence
  • Non-performing loans

ASJC Scopus subject areas

  • Finance

Fingerprint

Dive into the research topics of 'Determinants of non-performing loans: an explainable ensemble and deep neural network approach.'. Together they form a unique fingerprint.

Cite this