<![CDATA[Forecasting gold prices is essential for investors to minimize risks in investment decision-making. This study aims to predict gold closing prices using the Long Short-Term Memory (LSTM) method with weekly and monthly time frames. The data used were obtained from investing.com, covering the period from February 2015 to February 2025. The model's performance was evaluated using MAPE, RMSE, and R² metrics. The results show that the LSTM model has a good accuracy level, with MAPE values of 1.83% for the weekly time frame and 3.60% for the monthly time frame. The R² values of 0.9721 and 0.9134, respectively, indicate a high capability of the model in explaining data variability. Forecast results for the next 22 weeks indicate a stable trend with slight increases, while the 12-month forecast suggests a gradual downward trend in gold prices. These findings are expected to assist investors in planning more effective and measured investment strategies.]]>
Copyrights © 2026
