STOCK PRICE PREDICTION USING THE LONG SHORT-TERM MEMORY METHOD

Stocks are a highly risky investment instrument if not handled correctly. Therefore, accurately predicting stock prices is crucial to supporting better investment decisions. Today, more young people in the current generation know the importance of investing in stocks. Hence, understanding prediction methods early on is essential to reduce potential losses for prospective investors. With accurate prediction methods, the results will be more reliable. The data used consists of daily stock prices of Bank Syariah Indonesia from May 2019 to May 2024, totaling 1,215 data points. The research method employs LSTM (Long Short-Term Memory), which includes data collection, preprocessing, LSTM model formation, and model evaluation. The LSTM model is implemented using the Python programming language, and model evaluation is conducted using the Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) metrics. The results show that the LSTM model can provide accurate predictions with a MAPE error value of only 1.72% and an RMSE of 53.49. This research indicates that the LSTM method is effective in predicting stock prices with an accuracy level of 98.28% and can be one of the bases when starting stock investment.