We use a machine-learning algorithm known as boosted regression trees (BRT) to implement an orthogonality test of the rationality of aggregate stock-market forecasts. The BRT algorithm endogenously selects the predictor variables used to proxy the information set of forecasters so as to maximize...

Utilizing data from the German DAX30 stock index, we investigate whether local analysts have an informational advantage in forecasting stock returns. We analyze whether banks' buy and sell recommendations improve on the out-of-sample predictability of daily stock returns and the market-timing...