Cross-stock momentum builds on the asymmetry in lead-lag linkages and the difference between long-run and short-run contemporaneous co-movements. Data-driven cross-stock linkages generate a monthly alpha of 1.62% ( t -stat=10.03). The asymmetry distinguishes cross-stock momentum from factor momentum, and industry momentum is not subsumed by factor momentum. Factor momentum profit is mostly due to the high cross-stock links. The data-driven linkages vary faster over time than those in previous studies because short-run co-movements incorporate persistent linkages.

We present a novel methodology for the out-of-sample forecast of the equity premium. Our predictive slope coefficient is a conservative constant that has a lower bias than the zero slope employed by the historical average, but has the same variance. We demonstrate that, theoretically and empirically, our method dominates the historical average in forecast performance. Our methodology establishes a simple yet powerful paradigm for exploiting the real-time equity premium predictability derived from a predictor. Applications of our method reveal that many predictors can forecast the equity premium, and that parameter estimates in previous studies add value to out-of-sample forecasts.