<![CDATA[Accurate stock price prediction remains a significant challenge in financial forecasting, particularly for emerging market stocks. This study investigates the efficacy of Long Short-Term Memory (LSTM) networks in forecasting the stock prices of Ecopetrol (EC), Colombia's largest oil and gas company. Using historical stock data from Yahoo Finance spanning September 18, 2018, to September 18, 2023, we developed an LSTM model to capture complex temporal patterns in the stock market. The model's performance was evaluated using a range of metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Scaled Error (MASE). The results demonstrate that the LSTM model achieves low MAE (0.2509652), MSE (0.11678666), and RMSE (0.34174064), alongside a MAPE of 2.071206, indicating high accuracy and reliability in predicting stock prices. Although the MASE of 1.125679 suggests that the model performs similarly to a naive forecasting approach, it still provides valuable insights into stock price movements. This study highlights the effectiveness of LSTM in handling sequential data and capturing intricate stock price patterns, while suggesting that future improvements could be made by optimizing the model further and integrating additional relevant features.]]>
Copyrights © 2024
