Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
This provides a practical and transparent tool for financial risk modeling, addressing interpretability needs in bond default prediction, though it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of predicting bond defaults in China's volatile market by proposing EMDLOT, an explainable multimodal deep learning framework that integrates numerical and textual data, resulting in improved recall, F1-score, and mAP over benchmarks like XGBoost and LSTM.
In recent years, China's bond market has seen a surge in defaults amid regulatory reforms and macroeconomic volatility. Traditional machine learning models struggle to capture financial data's irregularity and temporal dependencies, while most deep learning models lack interpretability-critical for financial decision-making. To tackle these issues, we propose EMDLOT (Explainable Multimodal Deep Learning for Time-series), a novel framework for multi-class bond default prediction. EMDLOT integrates numerical time-series (financial/macroeconomic indicators) and unstructured textual data (bond prospectuses), uses Time-Aware LSTM to handle irregular sequences, and adopts soft clustering and multi-level attention to boost interpretability. Experiments on 1994 Chinese firms (2015-2024) show EMDLOT outperforms traditional (e.g., XGBoost) and deep learning (e.g., LSTM) benchmarks in recall, F1-score, and mAP, especially in identifying default/extended firms. Ablation studies validate each component's value, and attention analyses reveal economically intuitive default drivers. This work provides a practical tool and a trustworthy framework for transparent financial risk modeling.