Abstract

STOCK MARKET TREND ANALYSIS WITH LONG SHORT-TERM MEMORY NETWORKS IN MACHINE LEARNING

Sandeep Yadav*, Samender Singh and Pushkal Kumar Shukla

Abstract

When someone plan their investment, it is not easy for them to follow the overall daily updates and analysis the complete past records as an investor. They often fall into trap of choosing their known or recommended stocks instead of choosing a stock that has potential for giving them better result and profit based on analysis. Learning to forecast the stock market's investing strategies requires in-depth research of a large amount of data. We believe that the application of AI and machine learning techniques, which are now more prevalent than traditional methodology and approaches, can improve stock market forecasting. A recent breakthrough is the use of machine learning in the field of stock market forecasting. By training from previous values, this system generates projections depending on the stock market's current values indexes. Machine learning itself employs a variety of models to support and confirm prediction. The study focuses on machine learning using LSTM along with RNN for valuation of stock. Factors include volume, open, close, low, and high. Making it extremely challenging to predict future price changes. To comprehend the long-term dependency of stock prices, deep learning approaches, such as the LSTM approach, are utilised to gather lengthier data reliance and overall stock change patterns.

Keywords: Stock Market, Prediction, LSTM, RNN, unsupervised.