PREDIKSI HARGA DAGING SAPI DI KOTA JAKARTA PUSAT MENGGUNAKAN LSTM DAN GRU

This study analyzes the performance of two algorithms, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in predicting data from the PIHPS website, focusing on beef commodity prices. The dataset was divided into two proportions: 80:20 and 70:30, and evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and coefficient of determination (R²). The experimental results showed that GRU with 128 units and a 70:30 proportion achieved the best performance, with metrics of MAE at 170, RMSE at 390.2889, and R² at 0.902. The goal of this research is to determine the most suitable algorithm and unit configuration for this dataset. Future research is expected to integrate additional data with more complex models to improve prediction accuracy.