Stock return predictability in the frequency domain

This paper investigates the role of time–frequency information in dimension reduction prediction of stock returns. Using the long-term wavelet component of monthly S&P500 excess returns as supervision, we employ a machine learning method to extract the common predictive factor from prevalent macroeconomic variables and construct a new macroeconomic index aligned with stock return prediction. The macroeconomic index exhibits significant predictive power, both in and out of sample, at the market and portfolio levels. It outperforms all individual macroeconomic predictors and the factors based on higher frequency information of realized returns. Our findings demonstrate substantial economic value of the new index in asset allocation. Moreover, we also observe a complementary relation between macroeconomic index and investor sentiment. The predictive power is most pronounced during high-economic-uncertainty periods when investors are likely to underreact to fundamental signals and stems from cash flow predictability channel.