This paper quantifies the impact of stock-specific news sentiment on future financial returns. Predictive regressions yield significant t-statistics for 7% at most of our sample of more than one thousand large stocks listed in the US. While a few assets do run through pockets of predictability,...

We propose a linearization of rule-based algorithms that reveals the most important interactions between characteristics and macroeconomic variables when explaining future stock returns. Our results suggest that the two types of predictors are intertwined, which implies that the relationships...

We propose a linearization of rule-based algorithms that reveals the most important interactions between characteristics and macroeconomic variables when explaining future stock returns. Our results suggest that the two types of predictors are intertwined, which implies that the relationships...