LendNova: Towards Automated Credit Risk Assessment with Language Models

TL;DR

LendNova introduces an automated credit risk assessment pipeline using language models to analyze raw credit records, reducing manual effort and improving scalability in financial risk evaluation.

Contribution

It presents the first practical end-to-end system leveraging NLP and language models for direct analysis of raw credit data, bypassing manual feature engineering.

Findings

Effective risk signal extraction from raw text

Reduced manual preprocessing costs

Potential for scalable, accurate credit risk assessment

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.