Harshwardhan Patil and Rahul Patil, Pimpri Chinchwad College of Engineering, India

Unpredictable stock price forecasting is a difficult task due to the markets' flexible and unconditionally volatile nature. views into the machine learning meadow with the impending emotive and quantitative strategy. Increasing computational capabilities, software-based statistical medium of prognosis, and inventive method of prognosticating the model are all combined. In this study, the next due day-closing prices of Indian equities SBIN and Tatamotors are used to compare the long short term memory, Random Forest, and linear regression algorithms. Utilizing the RMSE standard layout indication, the prototypes are assessed. The low value of this indicator results in the most accurate closing price prediction model when compared to others.

Random Forest Regression, Long-Short Term Memory, Stock Price Prognosis.