Scholarlink

<p>Systemic risk monitoring and early warning systems for commercial banks are essential for maintaining financial stability and enhancing regulatory effectiveness. This study presents an innovative framework that integrates sentiment analysis with deep learning architectures to significantly improve risk prediction accuracy. We develop a novel sentiment index using text mining techniques applied to online public opinion data, combined with Time-Varying Parameter Vector Autoregression (TVP-VAR) modeling to capture dynamic inter-bank sentiment spillovers. This sentiment index is subsequently incorporated into a comprehensive risk early warning system powered by a Bidirectional Long Short-Term Memory network with Attention Mechanism (BiLSTM-AM). Our empirical analysis, based on data from 24 Chinese commercial banks (2017–2023), demonstrates substantial improvements: the BiLSTM-AM model reduces Mean Squared Error (MSE) by 25.2% compared to baseline models (from 0.3901 to 0.2917). Furthermore, the sentiment index exhibits superior predictive capability, providing warning signals 2–3&#xa0;months ahead of traditional indicators. The attention mechanism analysis reveals that sentiment indicators receive 35–45% higher attention weights during pre-crisis periods compared to conventional macroeconomic variables. These findings provide actionable insights for regulatory authorities implementing AI-driven risk monitoring systems and contribute to the broader literature on financial stability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on Systemic Risk Monitoring and Early Warning of Commercial Banks Based On Deep Learning

  • 期刊论文

  • 发表日期：

    2026年8月4日

查看全文
  • Min Xia,
  • Shuaiqi Lu

摘要

Systemic risk monitoring and early warning systems for commercial banks are essential for maintaining financial stability and enhancing regulatory effectiveness. This study presents an innovative framework that integrates sentiment analysis with deep learning architectures to significantly improve risk prediction accuracy. We develop a novel sentiment index using text mining techniques applied to online public opinion data, combined with Time-Varying Parameter Vector Autoregression (TVP-VAR) modeling to capture dynamic inter-bank sentiment spillovers. This sentiment index is subsequently incorporated into a comprehensive risk early warning system powered by a Bidirectional Long Short-Term Memory network with Attention Mechanism (BiLSTM-AM). Our empirical analysis, based on data from 24 Chinese commercial banks (2017–2023), demonstrates substantial improvements: the BiLSTM-AM model reduces Mean Squared Error (MSE) by 25.2% compared to baseline models (from 0.3901 to 0.2917). Furthermore, the sentiment index exhibits superior predictive capability, providing warning signals 2–3 months ahead of traditional indicators. The attention mechanism analysis reveals that sentiment indicators receive 35–45% higher attention weights during pre-crisis periods compared to conventional macroeconomic variables. These findings provide actionable insights for regulatory authorities implementing AI-driven risk monitoring systems and contribute to the broader literature on financial stability.