Analisis Perbandingan Metode ARIMA Dan LSTM Untuk Prediksi Penjualan Harga Saham BNI

Tunggal, Anisa
Prathivi, Rastri

Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Vol 6, No 1 (2025): Edisi Januari

This study aims to compare the Autoregressive Integrated Moving Average (ARIMA) model and Long Short-Term Memory (LSTM) in predicting the closing stock prices of Bank Negara Indonesia (BNI) from September 2021 to September 2024. Historical stock data was obtained through web scraping from Yahoo Finance and analyzed using evaluation metrics such as MAPE and RMSE. The results show that ARIMA outperforms LSTM in prediction accuracy, with lower MAPE and RMSE values for both training and testing data. Additionally, the 7-day ahead stock price predictions indicate that LSTM experienced a 3.42% decrease compared to ARIMA. Based on this study, ARIMA can be concluded as a more accurate model in predicting BNI stock prices compared to LSTM