Can Ensemble Machine Learning Methods Predict Stock Returns for Indian Banks Using Technical Indicators?

This paper develops ensemble machine learning models (XGBoost, Gradient Boosting, and AdaBoost in addition to Random Forest) for predicting stock returns of Indian banks using technical indicators. These indicators are based on three broad categories analysis: Price, Volume, Turnover. Various error metrics like Mean Absolute Error (MAE), Squared (MSE), Percentage (MAPE), Root-Mean-Squared-Error (RMSE) have been used check the performance models. Results show that XGBoost algorithm performs best among four The mean absolute root-mean-square -error vary around 3–5%. feature importance plots generated by depict variables output. proposed help traders, investors, as well portfolio managers, better predict market trends and, turn, returns, particularly banking stocks minimizing their sole dependency macroeconomic factors. techniques further assist participants pre-empting any price-volume action across irrespective size, liquidity, or past turnover. Finally, incredibly robust display a strong capability trend forecasts, with large deviations.