Realized Stock-Market Volatility: Do Industry Returns Have Predictive Value?

Yes, they do. Utilizing a machine-learning technique known as random forests to compute predictions of realized (good and bad) stock-market volatility, we show that incorporating the information in lagged industry returns can help improve out-of-sample predictions of aggregate stock-market volatility. While the predictive contribution of industry level returns is not constant over time, industrials and materials play a dominant predictive role during the aftermath of the 2008 global financial crisis, highlighting the informational value of real economic activity on stock-market volatility dynamics. Finally, we show that incorporating lagged industry returns in aggregate level volatility predictions is beneficial particularly when under-predicting market volatility is costly, yielding greater economic benefits as the degree of risk aversion increases.