<![CDATA[Exchange rates are a key indicator of a country’s economic condition and are inherently volatile and difficult to predict. Indonesian Rupiah exchange rate against Saudi Arabian Riyal (SAR) exhibits complex time series characteristics influenced by various macroeconomic factors. This study aims to forecast the Rupiah–SAR exchange rate using the Long Short-Term Memory (LSTM) method. The dataset consists of secondary data obtained from Bank Indonesia, covering the period from January 2, 2015, to February 27, 2026, with a total of 2,725 observations. The research methodology includes data preprocessing, transformation using a sliding window approach, data splitting, and LSTM modeling with hyperparameter tuning. The best performing model from the research results shows that achieved with a 90:10 train–test split, using 32 LSTM units, a learning rate of 0.001, 100 epochs, a dropout rate of 0.1, and a batch size of 32, yielding a Mean Absolute Percentage Error (MAPE) of 0.240376%, which falls into the highly accurate category. The 30-day forecasting results show a gradual downward trend in the exchange rate. These findings suggest that the LSTM model not only provides high predictive accuracy but also effectively captures the underlying nonlinear dynamics and temporal dependencies of exchange rate movements. Furthermore, the results reflect broader economic interactions, indicating that the model outputs can be utilized as a practical reference for financial planning and economic decision-making.]]>
Copyrights © 2026
