Stock Price Prediction Using Machine Learning

Stock prices are highly dynamic and nonlinear, making accurate prediction a significant challenge in financial markets. This study explores the application of various deep learning models, including Long Short-Term Memory (LSTM), BiLSTM, GRU, and BiGRU, for stock price forecasting. These models are well-suited for detecting temporal relationships in time-series data, such as stock prices. The financial time-series data of Google from 2016 to 2024 was preprocessed and split for training and testing. Model performance was evaluated using metrics like Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Accuracy. LSTM exhibited the best performance, achieving 98.57% accuracy with the lowest error metrics. Comparative analysis with other models confirmed the superior ability of LSTM in capturing market trends, suggesting its potential as a valuable tool for investors and financial analysts in making informed decisions.