PERBANDINGAN MODEL LSTM DAN GRU UNTUK MEMPREDIKSI HARGA MINYAK GORENG DI INDONESIA

Cooking oil, a food ingredient used for cooking, has increased in price Indonesia. Based on the Indonesian Strategic Food Price Center data, cooking oil reached twice regular at beginning of 2022. Long Short-Term Memory and Gated Recurrent Units are several ways to predict time domain data. The data set prediction is last three years taken pre-processed by changing type filling blank day with previous day's value. Data that been modeled using Units. Modeling obtained Error, Loss, selection best unit dropout model parameters making predictions both types models. As result, this research compared results Unit changes will occur during following year.