International Research Journal of Education and Technology

Stock price prediction is the process of forecasting future stock prices by analyzing historical market data. Accurate prediction helps investors make better financial decisions and manage investment risks. Traditional approaches such as technical analysis and fundamental analysis have been widely used to study stock market trends. However, due to the highly dynamic and volatile nature of the stock market, these methods often struggle to provide precise predictions.In recent years, machine learning and deep learning techniques have been introduced to improve the accuracy of stock price prediction. Among these techniques, the Long Short-Term Memory (LSTM) regression model has gained significant attention because of its ability to capture long-term dependencies and temporal patterns in time-series data. This project focuses on applying the LSTM regression algorithm to predict stock prices using historical stock market data.The model is trained using past stock price information and evaluated using performance metrics such as Mean Squared Error (MSE) and R-squared values. The results demonstrate that the LSTM model can effectively learn complex patterns in stock price movements and provide reliable predictions. Overall, the study highlights the potential of LSTM-based models in improving stock market prediction accuracy.