Multimodal Insights into Credit Risk Modelling: Integrating Climate and Text Data for Default Prediction

TL;DR

This paper presents a multimodal AI framework combining structured, climate, and textual data to improve credit default prediction for micro and small enterprises, highlighting climate risks' influence.

Contribution

It introduces a novel multimodal learning architecture integrating climate and text data into credit risk modeling, enhancing predictive accuracy.

Findings

Unimodal climate and text models outperform traditional structured data models.

Multimodal integration significantly improves default prediction accuracy.

Climate risks, especially water-logging, are key factors in default prediction.

Abstract

Credit risk assessment increasingly relies on diverse sources of information beyond traditional structured financial data, particularly for micro and small enterprises (mSEs) with limited financial histories. This study proposes a multimodal framework that integrates structured credit variables, climate panel data, and unstructured textual narratives within a unified learning architecture. Specifically, we use long short-term memory (LSTM), the gated recurrent unit (GRU), and transformer models to analyse the interplay between these data modalities. The empirical results demonstrate that unimodal models based on climate or text data outperform those relying solely on structured data, while the integration of multiple data modalities yields significant improvements in credit default prediction. Using SHAP-based explainability methods, we find that physical climate risks play an important role in default prediction, with water-logging by rain emerging as the most influential factor. Overall, this study demonstrates the potential of multimodal approaches in AI-enabled decision-making, which provides robust tools for credit risk assessment while contributing to the broader integration of environmental and textual insights into predictive analytics.