A Novel Approach to predict the Stock Price using LSTM and Linear Regression

Abstract

Stock price prediction is a challenging and crucial task in financial markets. Traditional methods often struggle to capture the complex patterns present in stock price movements. In this study, we propose a hybrid model combining Long Short-Term Memory (LSTM) and Linear Regression techniques to improve the accuracy and robustness of stock price predictions. We evaluate the performance of our hybrid model using historical stock price data and compare it with individual LSTM and linear regression models. The experiments demonstrate that the hybrid model outperforms the standalone models in terms of accuracy and robustness.