Does Overnight News Explain Overnight Returns?

2025-07-06

AI Summary

This study investigates whether the well-documented concentration of U.S. equity returns in overnight hours—rather than intraday hours—is driven by overnight news. Leveraging 2.4 million financial news articles and high-frequency market data, we propose a novel supervised topic modeling framework wherein market returns serve as the supervisory signal to identify news topic distributions and their time-varying market response heterogeneity. Results show that overnight news exhibits significantly higher information content, distinct thematic structure, and stronger market impact compared to intraday news—constituting a key mechanism underlying overnight return dominance and intraday return weakness. Our model robustly predicts stock-specific overnight excess returns and intraday return reversals, achieving substantially higher out-of-sample forecasting accuracy than conventional benchmarks. This work pioneers the integration of supervised text analytics with market microstructure analysis, offering a new paradigm for understanding how temporal asymmetries in information arrival shape asset returns.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Information Extraction
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Web Mining and Content Analysis: Topic discovery and tracking
• Economics, Online Markets and Human Computation: The sharing economy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Over the past 30 years, nearly all the gains in the U.S. stock market have been earned overnight, while average intraday returns have been negative or flat. We find that a large part of this effect can be explained through features of intraday and overnight news. Our analysis uses a collection of 2.4 million news articles. We apply a novel technique for supervised topic analysis that selects news topics based on their ability to explain contemporaneous market returns. We find that time variation in the prevalence of news topics and differences in the responses to news topics both contribute to the difference in intraday and overnight returns. In out-of-sample tests, our approach forecasts which stocks will do particularly well overnight and particularly poorly intraday. Our approach also helps explain patterns of continuation and reversal in intraday and overnight returns. We contrast the effect of news with other mechanisms proposed in the literature to explain overnight returns.

Problem

• Explains overnight stock returns using news features
• Analyzes 2.4M articles to link news topics to returns
• Forecasts stock performance differences intraday vs overnight

Innovation

• Supervised topic analysis for news impact
• 2.4 million news articles analyzed
• Forecasts stock performance using news