<![CDATA[Stocks are one of the most popular investment instruments among the public due to their potential for long-term returns through price appreciation and dividend distributions; however, stock price movements are heavily influenced by various factors such as macroeconomic conditions, market sentiment, and corporate actions, making accurate forecasting essential for investors to minimize risk and maximize profit. PT Bank BJB Tbk (ticker code: BJBR), a major bank in Indonesia that operates both conventional and Sharia-based services, has shown high volatility over the past few. Therefore, this research aims to develop a stock price prediction model for BJBR using the Long Short-Term Memory (LSTM) approach, a variant of Recurrent Neural Networks (RNN) well-suited for time series data. Historical closing price data from January 2020 to June 2025 were collected, preprocessed through normalization, dataset division, and transformation into supervised learning format, and then used to train an LSTM model with a two-layer architecture and dropout layers to prevent overfitting. The model was trained using the Adam optimizer and evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). Evaluation results showed that the model achieved a high level of accuracy, with an R² value of 0.9643 on the test data, while visualizations of predicted versus actual prices demonstrated a strong alignment, proving that the LSTM model is effective in capturing temporal patterns in financial time series data and can serve as a valuable tool for data-driven investment decision-making.]]>
