The instability of stock price movements has a significant impact on both companies and investors. The unpredictability of stock prices can affect the company's value, its image in the capital market, and its funding potential. For investors, the volatile stock price movements can influence their investment decisions. This study aims to implement data mining techniques in stock price prediction using the LSTM method to address the issues arising from stock price instability. By doing so, companies can identify the factors affecting stock price movements and make better decisions in managing their stocks. Additionally, investors can gain insights and predictions about stock price movements to make informed investment choices. The research uses data taken from Yahoo Finance website, specifically the stock price of PT Bank Central Asia from January 4, 2021, to March 21, 2023, with attributes such as date representing the stock's date and close representing the closing price for each day. The study involves building a web-based system using the Python programming language for stock price prediction using the LSTM method. The research results will be evaluated using Mean Absolute Percentage Error (MAPE) to determine the accuracy level of predictions, which yielded a value of 4.11% with a category of excellent prediction capability. Furthermore, the system will be tested for its functionality using the blackbox testing method, and the results show that the system functions as intended.