Prediction of share market stock price using long short-term memory and compare accuracy with Gaussian algorithm.

Examining how well the Gaussian Algorithm and Novel Long Short-Term Memory (LSTM) perform in predicting stock market outcomes is the main objective of this study. Using freely available data from the National Stock Exchange (NSE), this paper's dataset demonstrates the method's usefulness. To forecast the stock price of a corporation, we used G-power 0.8, alpha=0.05, beta=0.2, and a 95% range of confidence. Two hundred and eighty-two people took part; 140 were split evenly between Group 1 and Group 2. Predictions of stock market prices are made more accurate and precise when a ten-person sample uses the Gaussian Algorithm and Novel Long Short-Term Memory. The results demonstrate that the Novel Long Short-Term Memory classifier achieves a much superior accuracy rate of 93.94% when compared to the Gaussian Algorithm's 74.88%. The study found a significant value of p<0.05, which is the same as p=0.0271. Stock market forecasts made using Novel Long Short-Term Memory are more accurate and precise than those made using the Gaussian Algorithm. [ABSTRACT FROM AUTHOR]