Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction

• URL: http://arxiv.org/abs/2509.10802v1
• Date: Sat, 13 Sep 2025 03:42:34 GMT
• Title: Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
• Authors: Yi Lu, Aifan Ling, Chaoqun Wang, Yaxin Xu,
• Abstract summary: We propose a novel framework for multi-class bond default prediction.<n>LOT integrates numerical time-series (financial/macroeconomic indicators) and unstructured data (bondes)<n>It uses Time-Aware LSTM to handle irregular sequences, and adopts soft clustering and multi-level attention to boost interpretability.
• Score: 4.838838129678638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• $φ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models [58.217707070069885]
  This paper presents a novel Fairness Direct Preference Optimization (FaiDPO or $$-DPO) framework for continual learning in LMMs.<n>We first propose a new continual learning paradigm based on Direct Preference Optimization (DPO) to mitigate catastrophic forgetting by aligning learning with pairwise preference signals.<n> Extensive experiments and ablation studies show the proposed $$-DPO achieves State-of-the-Art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-02-26T04:14:33Z)
• Uncovering Representation Bias for Investment Decisions in Open-Source Large Language Models [0.06749750044497731]
  This paper focuses on representation bias in open-source Qwen models.<n>Using statistical tests and variance analysis, we find that firm size and valuation consistently increase model confidence.<n>When models are prompted for specific financial categories, their confidence rankings best align with fundamental data, moderately with technical signals, and least with growth indicators.
  arXiv  Detail & Related papers  (2025-10-07T09:10:13Z)
• Your AI, Not Your View: The Bias of LLMs in Investment Analysis [55.328782443604986]
  Large Language Models (LLMs) face frequent knowledge conflicts due to discrepancies between pre-trained parametric knowledge and real-time market data.<n>This paper offers the first quantitative analysis of confirmation bias in LLM-based investment analysis.<n>We observe a consistent preference for large-cap stocks and contrarian strategies across most models.
  arXiv  Detail & Related papers  (2025-07-28T16:09:38Z)
• Can We Reliably Predict the Fed's Next Move? A Multi-Modal Approach to U.S. Monetary Policy Forecasting [2.6396287656676733]
  This study examines whether predictive accuracy can be enhanced by integrating structured data with unstructured textual signals from Federal Reserve communications.<n>Our results show that hybrid models consistently outperform unimodal baselines.<n>For monetary policy forecasting, simpler hybrid models can offer both accuracy and interpretability, delivering actionable insights for researchers and decision-makers.
  arXiv  Detail & Related papers  (2025-06-28T05:54:58Z)
• Cross-Modal Temporal Fusion for Financial Market Forecasting [3.0756278306759635]
  We introduce a transformer-based deep learning framework, Cross-Modal Temporal Fusion (CMTF), that fuses structured and unstructured financial data for improved market prediction.<n> Experimental results using FTSE 100 stock data demonstrate that CMTF achieves superior performance in price direction classification compared to classical and deep learning baselines.
  arXiv  Detail & Related papers  (2025-04-18T07:20:18Z)
• FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting [58.70072722290475]
  Financial time series (FinTS) record the behavior of human-brain-augmented decision-making.<n>FinTSB is a comprehensive and practical benchmark for financial time series forecasting.
  arXiv  Detail & Related papers  (2025-02-26T05:19:16Z)
• Advanced Risk Prediction and Stability Assessment of Banks Using Time Series Transformer Models [10.79035001851989]
  This paper proposes a prediction framework based on the Time Series Transformer model.<n>We compare the model with LSTM, GRU, CNN, TCN and RNN-Transformer models.<n>The experimental results show that the Time Series Transformer model outperforms other models in both mean square error (MSE) and mean absolute error (MAE) evaluation indicators.
  arXiv  Detail & Related papers  (2024-12-04T08:15:27Z)
• BreakGPT: Leveraging Large Language Models for Predicting Asset Price Surges [55.2480439325792]
  This paper introduces BreakGPT, a novel large language model (LLM) architecture adapted specifically for time series forecasting and the prediction of sharp upward movements in asset prices. We showcase BreakGPT as a promising solution for financial forecasting with minimal training and as a strong competitor for capturing both local and global temporal dependencies.
  arXiv  Detail & Related papers  (2024-11-09T05:40:32Z)
• Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Markets [84.90242084523565]
  Traditional time-series econometric methods often appear incapable of capturing the true complexity of the multi-level interactions driving the price dynamics. By adopting a state-of-the-art second-order optimization algorithm, we train a Bayesian bilinear neural network with temporal attention. By addressing the use of predictive distributions to analyze errors and uncertainties associated with the estimated parameters and model forecasts, we thoroughly compare our Bayesian model with traditional ML alternatives.
  arXiv  Detail & Related papers  (2022-03-07T18:59:54Z)
• Gaussian process imputation of multiple financial series [71.08576457371433]
  Multiple time series such as financial indicators, stock prices and exchange rates are strongly coupled due to their dependence on the latent state of the market. We focus on learning the relationships among financial time series by modelling them through a multi-output Gaussian process.
  arXiv  Detail & Related papers  (2020-02-11T19:18:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.