<![CDATA[Stock price prediction remains a significant challenge in financial markets due to the high volatility and complexity of influencing factors. This study explores the application of hybrid models combining Decision Tree (DT) and Neural Network (NN) methodologies to enhance stock price prediction accuracy. The research utilizes extensive historical market data as the foundational input for training both models individually. The Decision Tree model is employed for its interpretability and ability to handle non-linear relationships, while the Neural Network model capitalizes on its capacity to learn complex patterns through its layered architecture. After training and evaluating each model separately, a hybrid approach is introduced, which averages the predictions from both the DT and NN models. Performance is quantitatively assessed using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results indicate that the hybrid model consistently outperforms individual models, achieving an MAE of 5.6 and RMSE of 7.94, with an overall accuracy of 91.5%. This fusion of methodologies demonstrates improved accuracy and significantly reduces error margins, showcasing the complementary strengths of both algorithms. The findings suggest that leveraging hybrid models can effectively mitigate risks associated with market fluctuations and enhance investment strategies. This research contributes to the field of financial forecasting by providing investors with more robust tools for making informed decisions, and offers recommendations for future research directions in integrating machine learning techniques for financial prediction.]]>
