Interpretable Systematic Risk around the Clock

2026-04-15

AI Summary

This study investigates the identification, interpretation, and pricing of news-driven systematic jump risk in all-weather high-frequency markets. By integrating high-frequency price data with real-time news feeds, the authors leverage an open-source large language model (LLM) to automatically retrieve and semantically classify news events that trigger market jumps, thereby achieving the first interpretable decomposition of systematic jump risk. They construct factor-mimicking portfolios based on this decomposition and validate their pricing power using Fama-MacBeth cross-sectional regressions. Empirical results reveal significant heterogeneity in jump risk premia across news categories. An annually rebalanced portfolio derived from this approach delivers a high out-of-sample Sharpe ratio and generates significant alpha relative to established multifactor models, demonstrating the efficacy of LLM-enabled real-time risk identification and asset pricing.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

In this paper, I present the first comprehensive, around-the-clock analysis of systematic jump risk by combining high-frequency market data with contemporaneous news narratives identified as the underlying causes of market jumps. These narratives are retrieved and classified using a state-of-the-art open-source reasoning LLM. Decomposing market risk into interpretable jump categories reveals significant heterogeneity in risk premia, with macroeconomic news commanding the largest and most persistent premium. Leveraging this insight, I construct an annually rebalanced real-time Fama-MacBeth factor-mimicking portfolio that isolates the most strongly priced jump risk, achieving a high out-of-sample Sharpe ratio and delivering significant alphas relative to standard factor models. The results highlight the value of around-the-clock analysis and LLM-based narrative understanding for identifying and managing priced risks in real time.

Problem

• systematic jump risk
• around-the-clock analysis
• news narratives
• risk premia
• interpretable risk

Innovation

• systematic jump risk
• around-the-clock analysis
• LLM-based narrative classification
• risk premia heterogeneity
• factor-mimicking portfolio