Perbandingan Metode GARCH, LSTM, GRU, dan CNN pada Peramalan Volatilitas Kurs

Currency volatility is an important aspect of time series data analysis in economics and finance. This study aims to compare the performance of four methods: Generalized Autoregressive Conditional Heteroscedasticity (GARCH), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN), in predicting the volatility of the Rupiah against the US Dollar. The data used is daily exchange rates from January 2015 to March 2024. The evaluation is conducted by calculating the Root Mean Square Error (RMSE) and the percentage of actual values within a 95% confidence interval on training and testing data. The results indicate that LSTM achieves the lowest RMSE, with values of 5.30E-05 on training data and 2.50E-05 on testing data, demonstrating high accuracy in capturing non-linear patterns and long-term fluctuations. GRU records the highest percentage of actual values within the confidence interval, at 90.32% for training data and 91.72% for testing data, reflecting superior consistency compared to other methods. Meanwhile, GARCH shows competitive performance but lacks robustness on testing data. CNN exhibits the lowest performance, with high RMSE and a low percentage of data within the confidence interval. Overall, GRU emerges as the best method, offering an optimal balance between predictive accuracy and consistency, making it a reliable tool for modeling exchange rate volatility in high-volatility scenarios. Consequently, GRU is utilized for forecasting exchange rate volatility for the next 30 days. These findings contribute to the selection of appropriate methods for modeling exchange rate volatility, particularly amidst global market uncertainty.