Direction is more important than speed: A comparison of direction and value prediction of stock returns
A major research topic in asset pricing is predicting the value of stock excess returns. We examine a seemingly simpler and yet less explored problem—–predicting the direction. Theoretically, mechanisms such as the Campbell-Shiller identity and volatility clustering can support direction predictability. Using various established predictors from value prediction literature, we compare linear, regularized linear, machine learning, and combination models across both tasks. When shifting from value to direction prediction, models achieve higher accuracy and yield greater economic gains, mainly because of their stronger ability to predict market downturns. Consistent with the value prediction literature, machine learning and combination methods generally outperform simpler models in direction prediction as well. While most models perform better when incorporating the full set of predictors, direction prediction with a limited set of predictors can still rival value prediction using a comprehensive set of predictors. Moreover, blending value and direction strategies outperforms value strategies but does not surpass direction-only results. We also find that the returns of direction strategies can explain the returns of value strategies, but not vice versa.
It seems that predicting the value of future stock returns has been an orthodox practice in the field of asset pricing since at least Sharpe (1964) and Ross (1976). The beautiful theory of factor model provides both explanatory and predictive implications for statistical exercises, inspiring a voluminous body of empirical literature. However, an often encountered layperson’s first question, while not naive, is: “Do you think the market will go up or down in the near future?”. In this paper we examine this question through the lens of empirical asset pricing and machine learning.