Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts
European Journal of Operational Research · 2025-11 · 326 (3) · 691-706
DOI: 10.1016/j.ejor.2025.04.032 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Operational Research, 2025-11. Verfasst von Zongxiao Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Social Science Fund of China, Dalian University of Technology, Yunnan University of Finance and Economics.
Abstract (Originalsprache)
This study explores the integration of a representative large language model, ChatGPT, into lending decision-making with a focus on credit default prediction. Specifically, we use ChatGPT to analyse and interpret loan assessments written by loan officers and generate refined versions of these texts. Our comparative analysis reveals significant differences between generative artificial intelligence (AI)-refined and human-written texts in terms of text length, semantic similarity, and linguistic representations. Using deep learning techniques, we show that incorporating unstructured text data, particularly ChatGPT-refined texts, alongside conventional structured data significantly enhances credit default predictions. Furthermore, we demonstrate how the contents of both human-written and ChatGPT-refined assessments contribute to the models' prediction and show that the effect of essential words is highly context-dependent. Moreover, we find that ChatGPT's analysis of borrower delinquency contributes the most to improving predictive accuracy. We also evaluate the business impact of the models based on human-written and ChatGPT-refined texts, and find that, in most cases, the latter yields higher profitability than the former. This study provides valuable insights into the transformative potential of generative AI in financial services.
Förderung
- National Social Science Fund of China
- Dalian University of Technology
- Yunnan University of Finance and Economics
- National Natural Science Foundation of China
- Nanjing Agricultural University
Zitieren
APA
Wu, Z., Dong, Y., Li, Y., & Shi, B. (2025). Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts. European Journal of Operational Research, 326(3), 691-706. https://doi.org/10.1016/j.ejor.2025.04.032
Vancouver
Wu Z, Dong Y, Li Y, Shi B. Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts. European Journal of Operational Research. 2025;326(3):691-706. doi:10.1016/j.ejor.2025.04.032
BibTeX
@article{Wu2025,
author = {Wu, Zongxiao and Dong, Yizhe and Li, Yaoyiran and Shi, Baofeng},
title = {Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts},
journal = {European Journal of Operational Research},
year = {2025},
volume = {326},
number = {3},
pages = {691--706},
doi = {10.1016/j.ejor.2025.04.032}
}
EUVIMED