Machine learning-driven credit risk: a systemic review

Si Shi, Rita Tse, Wuman Luo, Stefano D’Addona, Giovanni Pau

Research output: Contribution to journalReview articlepeer-review

21 Citations (Scopus)

Abstract

Credit risk assessment is at the core of modern economies. Traditionally, it is measured by statistical methods and manual auditing. Recent advances in financial artificial intelligence stemmed from a new wave of machine learning (ML)-driven credit risk models that gained tremendous attention from both industry and academia. In this paper, we systematically review a series of major research contributions (76 papers) over the past eight years using statistical, machine learning and deep learning techniques to address the problems of credit risk. Specifically, we propose a novel classification methodology for ML-driven credit risk algorithms and their performance ranking using public datasets. We further discuss the challenges including data imbalance, dataset inconsistency, model transparency, and inadequate utilization of deep learning models. The results of our review show that: 1) most deep learning models outperform classic machine learning and statistical algorithms in credit risk estimation, and 2) ensemble methods provide higher accuracy compared with single models. Finally, we present summary tables in terms of datasets and proposed models.

Original languageEnglish
Pages (from-to)14327-14339
Number of pages13
JournalNeural Computing and Applications
Volume34
Issue number17
DOIs
Publication statusPublished - Sept 2022

Keywords

  • Credit risk
  • Deep learning
  • Machine learning
  • Statistical learning

Fingerprint

Dive into the research topics of 'Machine learning-driven credit risk: a systemic review'. Together they form a unique fingerprint.

Cite this