LendNova: Towards Automated Credit Risk Assessment with Language Models

2026-01-05

arXiv.org

AI Summary

This work proposes the first end-to-end credit risk assessment framework that directly leverages raw, terminology-rich credit bureau narratives without relying on manual feature engineering or preprocessing. By harnessing advanced language models to automatically learn task-relevant representations from unstructured textual data in original credit reports, the approach overcomes the limitations of traditional methods that struggle to effectively utilize such information. Experimental results on real-world data demonstrate that the proposed framework not only achieves significantly higher predictive accuracy and computational efficiency but also substantially reduces modeling costs and enhances system scalability. These advantages establish a foundational technical pathway toward intelligent credit risk proxy systems capable of autonomously interpreting complex financial narratives.

Technology Category

Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP ModelsReasoning under Uncertainty: Relational Probabilistic ModelsMachine Learning: Feature Construction/Reformulation

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingWeb Mining and Content Analysis: Large pretrained models with web dataUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Credit risk assessment is essential in the financial sector, but has traditionally depended on costly feature-based models that often fail to utilize all available information in raw credit records. This paper introduces LendNova, the first practical automated end-to-end pipeline for credit risk assessment, designed to utilize all available information in raw credit records by leveraging advanced NLP techniques and language models. LendNova transforms risk modeling by operating directly on raw, jargon-heavy credit bureau text using a language model that learns task-relevant representations without manual feature engineering. By automatically capturing patterns and risk signals embedded in the text, it replaces manual preprocessing steps, reducing costs and improving scalability. Evaluation on real-world data further demonstrates its strong potential in accurate and efficient risk assessment. LendNova establishes a baseline for intelligent credit risk agents, demonstrating the feasibility of language models in this domain. It lays the groundwork for future research toward foundation systems that enable more accurate, adaptable, and automated financial decision-making.

Problem

• credit risk assessment
• raw credit records
• feature-based models
• financial decision-making
• automated risk modeling

Innovation

• credit risk assessment
• language models
• end-to-end automation
• natural language processing
• feature-free modeling