The high volatility and non-linearity of stock market data present significant challenges in forecasting price movements. This study aims to develop an accurate predictive model for the daily closing price of PT Bank Rakyat Indonesia (Persero) Tbk (BBRI) using a Long Short-Term Memory (LSTM) neural network. The primary objective is to enhance predictive accuracy by incorporating technical indicators—Relative Strength Index (RSI) and Moving Average Convergence Divergence (MACD)—into the model architecture. Historical stock data from 2010 to 2024 were collected from Yahoo Finance. The dataset was preprocessed through data cleaning, feature engineering, normalization, and time-based splitting into training and testing sets. The LSTM model was trained using the Mean Squared Error (MSE) loss function and optimized with the Adam optimizer. Model performance was evaluated based on key metrics including MSE, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The results indicate that the model performs effectively, with training RMSE of 73.61 and testing RMSE of 92.47. These findings demonstrate that the LSTM model, enriched with RSI and MACD indicators, is capable of capturing temporal patterns in stock prices and generating reliable forecasts. The study contributes to the growing body of literature on deep learning applications in financial forecasting, and offers practical insights for investors and analysts in understanding market behavior and supporting data-driven decision-making.