Cyber risk and the cross-section of stock returns

ArXiv ID: 2402.04775 “View on arXiv”

Authors: Unknown

Abstract

We extract firms’ cyber risk with a machine learning algorithm measuring the proximity between their disclosures and a dedicated cyber corpus. Our approach outperforms dictionary methods, uses full disclosure and not devoted-only sections, and generates a cyber risk measure uncorrelated with other firms’ characteristics. We find that a portfolio of US-listed stocks in the high cyber risk quantile generates an excess return of 18.72% p.a. Moreover, a long-short cyber risk portfolio has a significant and positive risk premium of 6.93% p.a., robust to all factors’ benchmarks. Finally, using a Bayesian asset pricing method, we show that our cyber risk factor is the essential feature that allows any multi-factor model to price the cross-section of stock returns.

Keywords: Machine Learning, Text Mining, Asset Pricing, Risk Factor, Cyber Risk, Equities

Complexity vs Empirical Score

• Math Complexity: 4.5/10
• Empirical Rigor: 7.0/10
• Quadrant: Street Traders
• Why: The paper employs advanced machine learning (Paragraph Vector) and Bayesian asset pricing methods, indicating moderate mathematical complexity. It demonstrates high empirical rigor with backtest-ready results, robustness checks, cross-sectional and time-series tests, and provides code availability on GitHub.

  flowchart TD
    A["Research Goal:<br>Can cyber risk explain<br>cross-section of stock returns?"] --> B["Text Mining & ML<br>Extract cyber risk from disclosures"]
    B --> C["Construct Portfolio<br>High vs Low cyber risk quantiles"]
    C --> D["Factor Analysis<br>Estimate risk premiums &<br>Benchmark against Fama-French factors"]
    D --> E["Bayesian Asset Pricing<br>Identify essential risk factor<br>for multi-factor models"]
    E --> F["Key Findings:<br>1. High risk portfolio: +18.72% p.a.<br>2. Long-short premium: +6.93% p.a.<br>3. Cyber risk factor is essential"]