International Journal of Scientific Research and Engineering Development

Predicting stock prices is inherently difficult because financial markets are complex and inherently unstable. Traditional statistical approaches have had a difficult time accounting for sometimes very complicated statistical and causal dependencies among different market indicators, as well as the influence of external factors on stock prices. This study presents a hybrid machine learning methodology that combines and implements various prediction algorithms with the goal of improving stability and accuracy of the forecasts. The model combines and leverages deep-learning techniques such as Long Short-term Memory (LSTM) neural networks, leveraging LSTM's strengths in recognizing temporal patterns, while utilizing ensemble methods such as Random Forest (RF) and Gradient Boosting (GBM) to learn features more robustly. In addition, to build and evaluate the proposed model, historical stock data, technical indicators, and analytic data from financial news was utilized. Several experiment findings showed that hybrid machine learning methods are superior to simple baseline models across various performance metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and directional accuracy. The proposed model suggests that hybrid machine learning models may be a viable method to enhance modeling and predictions of stock pricing, thus enabling investors and analysts to make better data-informed decisions and investments.

Ms.S.Revathi, Praveen L, Pranesh M,"Stock Price Prediction Using Hybrid ML Models" International Journal of Scientific Research and Engineering Development, V9(2): Page(1900-1904) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.