Transformer-based CoVaR: Systemic Risk in Textual Information

TL;DR

This paper introduces a Transformer-based approach that integrates raw financial news text with market data to improve systemic risk measurement via CoVaR, demonstrating enhanced predictive accuracy and insights during market stress periods.

Contribution

It develops a novel Transformer-based method that directly incorporates raw textual data into CoVaR estimation, with proven error bounds and improved risk forecasting performance.

Findings

Textual information significantly impacts CoVaR forecasts.

Transformer-based CoVaR outperforms traditional sentiment-based methods.

Market stress periods show pronounced risk signals in textual data.

Abstract

Conditional Value-at-Risk (CoVaR) quantifies systemic financial risk by measuring the loss quantile of one asset, conditional on another asset experiencing distress. We develop a Transformer-based methodology that integrates financial news articles directly with market data to improve CoVaR estimates. Unlike approaches that use predefined sentiment scores, our method incorporates raw text embeddings generated by a large language model (LLM). We prove explicit error bounds for our Transformer CoVaR estimator, showing that accurate CoVaR learning is possible even with small datasets. Using U.S. market returns and Reuters news items from 2006--2013, our out-of-sample results show that textual information impacts the CoVaR forecasts. With better predictive performance, we identify a pronounced negative dip during market stress periods across several equity assets when comparing the Transformer-based CoVaR to both the CoVaR without text and the CoVaR using traditional sentiment measures. Our results show that textual data can be used to effectively model systemic risk without requiring prohibitively large data sets.