<![CDATA[This study presents a novel approach to stock price prediction by employing Convolutional Neural Networks (CNNs) to forecast the stock prices of the Hellenic Telecommunications Organization (HTO.AT). The CNN model demonstrated exceptional predictive performance, achieving a Root Mean Squared Error (RMSE) of 0.22859211 and a Mean Absolute Percentage Error (MAPE) of 1.2041852, indicating a high level of accuracy. By effectively capturing complex and non-linear patterns in historical stock price data, the model surpasses traditional forecasting methods, thus offering significant advantages for investors and financial analysts. This research emphasizes the importance of integrating external data and exploring alternative deep learning architectures, such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks, to further enhance prediction capabilities. Overall, the findings underscore the potential of CNNs as powerful tools in financial market analysis, providing actionable insights for more informed investment decisions.]]>
Copyrights © 2024
