This study predicts stock splits using two ensemble machine learning techniques: gradient boosting machines (GBMs) and random forests (RFs). The goal is to form implementable portfolios based on positive predictions to generate abnormal returns. Since splits are rare events, we use SMOTE...

Whether higher idiosyncratic return volatility means more or less informative stock prices is an ongoing debate. All the existing literature relies on cross-sectional evidence, which makes it hard to isolate the effects of price informativeness on idiosyncratic volatility from other effects. I...

Whether higher idiosyncratic return volatility means more or less informative stock prices is an ongoing debate. All the existing literature relies on cross-sectional evidence, which makes it hard to isolate the effects of price informativeness on idiosyncratic volatility from other effects. I...