Komparasi Metode LSTM dan GRU dalam Memprediksi Harga Saham

Meri Aryati, Ni Wayan
Wiguna, I Komang Arya Ganda
Putri, Ni Wayan Suardiati
Widiartha, I Komang Kurniawan
Ginantra, Ni Luh Wiwik Sri Rahayu

JURNAL MEDIA INFORMATIKA BUDIDARMA
Vol 8, No 2 (2024): April 2024

The rapid development of technology has an impact on the economy of society, one of which is investing in stocks. Stocks are evidence of ownership of an individual's assets in a company. However, stock prices have very high levels of fluctuation, requiring accurate methods to assist in predicting stock prices. LSTM and GRU were chosen for their intrinsic ability to handle long-term and short-term problems in time series data. LSTM has a complex memory structure that allows decision-making based on long and short-term information. Meanwhile, GRU has a simpler structure with a focus on gate mechanisms to control information flow, resulting in lighter and faster models. Therefore, this study will compare two RNN methods, Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU), in predicting stock prices using MAPE and RMSE evaluation metrics. The combination of parameters used to evaluate the MAPE and RMSE values in this study includes learning rate, timestamps, batch size, and epoch. The results of this study show that the GRU method is more accurate compared to the LSTM method. This is evidenced by the evaluation results of the LSTM method with the lowest MAPE value of 2.42% and the lowest RMSE value of 0.01807, while the evaluation results of the GRU method with the lowest MAPE value of 2.14% and the lowest RMSE value of 0.01775. The combination of parameters used in this study also has an influence on the final MAPE and RMSE results, especially in the use of learning rates of 0.001 and 0.0001. Therefore, it can be concluded in this study that the GRU method is more accurate and effective compared to the LSTM method in predicting stock prices.