Predicting corporate policies using downside risk: A machine learning approach

Abstract

This paper develops a text-based downside risk measure using corporate annual reports and assesses its ability to forecast future corporate policies. The forward-looking measure dynamically captures adverse firm conditions evolving from economic fundamentals. When the measure is below its sample average, leverage, investment, R&D, employment, and dividends consistently fall. When the measure rises, firms increase cash holdings. The proposed measure also delivers robust and persistent forecasts based on in-sample and out-of-sample LASSO regressions. • Develop a text-based downside risk measure using corporate annual reports. • Forward-looking measure captures adverse firm conditions evolving from economic fundamentals. • Measure significantly predicts leverage, investment, R&D, employment, dividends and cash holdings. • Stronger predictive power than that of stock return volatility and earnings volatility. • Robust and persistent predictability based on in-sample and out-of-sample LASSO regressions.