Financial Forecasting with Machine Learning: Price Vs Return

Forecasting directional movement of stock price using machine learning tools has attracted a considerable amount research. Two the most common input features in forecasting model are and return. The choice between former latter variables is often subjective. In this study, we compare effectiveness return as models. We perform an extensive comparison two 10-year historical data ten large cap US companies. employ four popular classification algorithms basis models used our study. results show that more effective standalone feature than equalize when add technical indicators to set. conclude generally potent value predicting direction movement. Our should aid researchers practitioners interested applying forecasting.