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...

The explosion of online information with the recent advent of digital technology in information processing, information storing, information sharing, natural language processing, and text mining techniques has enabled stock investors to uncover market movement and volatility from heterogeneous...