<![CDATA[This study examines the effectiveness of the Long Short-Term Memory (LSTM) model in predicting stock price movements of Thai Oil Public Company Limited (TOP.BK). Using historical stock price data of the past five years, we apply the LSTM neural network architecture to model temporal patterns and predict future stock prices. The model is compared with traditional time series approaches such as ARIMA and other statistical models. Results show that the LSTM model optimized by Grid Search achieves excellent performance with Root Mean Square Error (RMSE) of 1.00 and Mean Absolute Error (MAE) of 0.75 on the test data, with prediction accuracy reaching 98.32%. The model also showed a high coefficient of determination (R²) of 0.8715 on the test data, demonstrating the model's ability to explain most of the variation in the data. This research proves that the LSTM model is highly effective for stock price prediction in the oil and gas industry, with important implications for investment strategies and risk management.]]>
Copyrights © 2024
