Forecasting the Equity Premium: Mind the News!
41 Pages Posted: 26 Apr 2019 Last revised: 16 May 2019
Date Written: April 18, 2019
This paper introduces a novel strategy for predicting monthly equity premia based on extracted news from more than 700,000 newspaper articles, published in The New York Times and Washington Post between 1980 and 2018. We propose a flexible data-adaptive switching approach for mapping a large set of different news-topics into forecasts of aggregate stock returns. The information embedded in our extracted news is not captured by established predictors. Compared to the prevailing historical mean between 1999 and 2018, we find large out-of-sample (OOS) gains with an R²OOS of 6.52% and sizeable utility gains for a mean-variance investor. The empirical results indicate that geopolitical news are more valuable than economic news and that gains arise in down markets.
Keywords: Topic Modeling, Big Data, Return Predictability, Text as Data
JEL Classification: G11, G12, G17, C53
Suggested Citation: Suggested Citation