We examine the effect of realized skewness on Chinese stock returns. We construct realized skewness by using intraday data at a monthly horizon. Our study finds a significant negative relation between realized skewness and future stock returns in both portfolio analyses and cross-sectional...

We examine return predictability with machine learning in 46 international stock markets. We calculate 148 stock characteristics and use them to feed a repertoire of different models. The algorithms extract predictability mainly from simple, yet popular, factor types—such as momentum,...