Sharia Bank of Indonesia Stock Price Prediction using Long Short-Term Memory

This study explored the applicability of Long Short-Term Memory (LSTM) networks for predicting the closing prices of Sharia Bank of Indonesia stock. Utilizing historical data and a rigorous hyperparameter tuning process, the LSTM model demonstrated exceptional accuracy in forecasting closing prices, achieving a Mean Absolute Percentage Error (MAPE) of 2.46%. This significantly surpasses the benchmark for "very good" forecasting performance. The findings underscore the potential of LSTM networks for accurate stock price prediction and provide a foundation for future research to incorporate additional financial indicators and explore more complex model architectures.