A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting

TL;DR

This paper introduces FinLangNet, a dual-architecture framework that models heterogeneous financial data at multiple scales to improve credit scoring accuracy and robustness.

Contribution

It proposes a novel dual-prompt mechanism within a multi-scale sequential learning framework for better financial data modeling.

Findings

Achieved a 6.3 percentage point improvement in KS metric.

Reduced bad debt rate by 9.9%.

Effectively models heterogeneous financial data across multiple time horizons.

Abstract

Recent industrial credit scoring models remain heavily reliant on manually tuned statistical learning methods. Despite their potential, deep learning architectures have struggled to consistently outperform traditional statistical models in industrial credit scoring, largely due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness. To bridge this gap, we introduce FinLangNet, a novel framework that reformulates credit scoring as a multi-scale sequential learning problem. FinLangNet processes heterogeneous financial data through a dual-module architecture that combines tabular feature extraction with temporal sequence modeling, generating probability distributions of users' future financial behaviors across multiple time horizons. A key innovation is our dual-prompt mechanism within the sequential module, which introduces learnable prompts operating at both feature-level granularity for capturing fine-grained temporal patterns and user-level granularity for aggregating holistic risk profiles. Notably, real world deployment yielded a 6.3 pp improvement in KS, along with a 9.9\% reduction in bad debt rate.