Stock Market Analysis and Prediction for Nifty50 using LSTM Deep Learning Approach

Abstract

Designing and developing a prediction model with an accurate stock price prediction has been an active field of research in the stock market for a long time. On the other hand, predicting stock price movement is the most critical aspect of the entire forecast process. While some market hypotheses argue that precisely predicting stock price movement is impossible, research shows that stock price movement can be expected to some extent. Stock price movement can be precisely measured if prediction models are correctly designed, developed, and refined. The Deep Learning (DL)-based Long Short-Term Memory (LSTM) Algorithm is proposed in this study. India's National Stock Exchange (NSE) provided us with ten years of historical stock price data for the NIFTY 50 index. The historical dataset was picked from 10 December 2011 to 10 December 2021. This dataset is used for model training and testing after normalized. The proposed model's results are pretty promising, with an accuracy of 83.88 percent.