Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models
Authors:
- Duanyu FengDFDuanyu Feng
- Yongfu DaiYDYongfu Dai
- Jimin HuangJHJimin Huang
- Yifang ZhangYZYifang Zhang
- Qianqian XieQXQianqian Xie
- Weiguang HanWHWeiguang Han
- Zhengyu ChenZCZhengyu Chen
- Alejandro Lopez-LiraALAlejandro Lopez-Lira
- Hao WangHWHao Wang
Preprint
Abstract
In the financial industry, credit scoring is a fundamental element, shaping access to credit and determining the terms of loans for individuals and businesses alike. Traditional credit scoring methods, however, often grapple with challenges such as narrow knowledge scope and isolated evaluation of credit tasks. Our work posits that Large Language Models (LLMs) have great potential for credit scoring tasks, with strong generalization ability across multiple tasks. To systematically explore LLMs for credit scoring, we propose the first open-source comprehensive framework. We curate a novel benchmark covering 9 datasets with 14K samples, tailored for credit assessment and a critical examination of potential biases within LLMs, and the novel instruction tuning data with over 45k samples. We then propose the first Credit and Risk Assessment Large Language Model (CALM) by instruction tuning, tailored to the nuanced demands of various financial risk assessment tasks. We evaluate CALM, existing state-of-art (SOTA) methods, open source and closed source LLMs on the build benchmark. Our empirical results illuminate the capability of LLMs to not only match but surpass conventional models, pointing towards a future where credit scoring can be more inclusive, comprehensive, and unbiased. We contribute to the industry's transformation by sharing our pioneering instruction-tuning datasets, credit and risk assessment LLM, and benchmarks with the research community and the financial industry.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Multi-modal deep learning for credit rating prediction using text and numerical data streamsApplied Soft Computing, 2025
- Deep reinforcement learning with the confusion-matrix-based dynamic reward function for customer credit scoringExpert Systems with Applications, 2022
- Novel hybrid ensemble credit scoring model with stacking-based noise detection and weight assignmentExpert Systems with Applications, 2022
- Data science and AI in FinTech: an overviewInternational Journal of Data Science and Analytics, 2021
- EGRNN++ and PNN++ : Parallel and Distributed Neural Networks for Big Data Regression and ClassificationSN Computer Science, 2021
- Explainable Machine Learning in Credit Risk ManagementComputational Economics, 2020
- Statistical and machine learning models in credit scoring: A systematic literature surveyApplied Soft Computing, 2020
- Machine learning techniques for credit risk evaluation: a systematic literature reviewJournal of Banking and Financial Technology, 2020
- A combined entropy-based approach for a proactive credit scoringEngineering Applications of Artificial Intelligence, 2020
- Rule-based credit risk assessment model using multi-objective evolutionary algorithmsExpert Systems with Applications, 2019