• Akhilesh Satish Gawade
• Maitreya Bhupesh Kocharekar
• Manal Ajit Vartak

Stock Market is a term which is known for its dynamic nature. In recent years, we have witnessed increasing attention towards the stock market by people across the world. People like investors, stockbrokers, and individuals who have an interest in the stock market have started investing their money with the hope that they will get good returns in the future. This tells us how important prediction is for those investing in the stock market. The objective of this paper is to predict the stock market price and its behaviour by using the concepts of LSTM and moving average to predict the data of Fortune-500 companies. This will give people an idea of what company to invest in. We have used our own moving average model along with LSTM to predict the prices of Fortune-500 companies, and we also did sentimental analysis of live tweets related to each individual company in our dataset, which will help in knowing the polarity of opinions about a company at that particular instant. We have used the past 12 years of data as input to our model, which we are currently implementing. Using our model, we were able to bring the losses down to just a meagre 0.6, which is something pristine and unique. Along with that, we received a very good MSE value of 0.032, which is also an ideal value as per many research papers and also an appropriate measure for evaluation.

Moving Average, Sentimental Analysis, Artificial Neural Networks, Stock Market, LSTM (Long Short-Term Memory), Machine Learning

"Stock Market Prediction Using LSTM and Moving Average", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 1, page no.c188-c193, January-2023, Available :http://www.jetir.org/papers/JETIR2301223.pdf

"Stock Market Prediction Using LSTM and Moving Average", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 1, page no. ppc188-c193, January-2023, Available at : http://www.jetir.org/papers/JETIR2301223.pdf