News volume information: Beyond earnings forecasting in a global stock selection model

Earnings forecasting models produce highly statistically significant asset selection, active equity, and total active returns. We propose a measure of abnormal news volume that controls for the size of the firm and the analyst attention that it receives, and demonstrate that news volume information can enhance returns relative to using only an earnings forecasting model. Furthermore, we show that this measure enhances the predictive power of a global stock selection model using information coefficients, Boolean signals, and efficient frontiers.