Forecasting share market’s imminent is a complex and challenging task, necessitating the examination of vast data and the evaluation of various political, social, and economic variables. Due to the intrinsic uncertainty and fluctuation of stock values, an investor consistently endeavors to identify ways for forecasting future trends to minimize losses and optimize profits. Modern developments in the areas of Machine Learning have enabled the application of diverse algorithms for stock price prediction. The paper delivers a inclusive study of different methods and tactics used in financial forecasting, encompassing fundamental evaluation. The research emphasizes the different techniques employed and evaluates their efficacy in forecasting stock market fluctuations. The present research intends to employ nine distinct methods: Regression, ARIMA, SVM, LSTM, CNN, RNN, LSTM – RNN, LSTM – CNN, and LSTM – PSO. The research presented here identifies algorithms that precisely represent real projections. These methodologies are implemented on NSE index data spanning from January 2008 to December 2018. This comprehensive analysis reveals that the deep learning algorithm surpasses all other algorithms in forecasting stock prices and time series, yielding findings with significant accuracy.