STOCK PRICE PREDICTION USING RANDOM FOREST REGRESSION

Abstract

Stock price forecasting is a prominent and fascinating research issue in the financial and academic industries for calculating the size of nations.There was nothing like that.A substantial set of criteria for determining and foreseeing the amount of a stock exchange share.Many natural technologies exist to assist us in trying the prediction process, such as expertise in fundamental, time, mathematical, and series analysis, but not one of these techniques have been established to people as a valid and precise tool in calculating the value of stock markets or share market scales.In this study, we attempted to do something innovative by applying a Machine Learning technique to foresee or sense the stock exchange sensex's conduct tracking.Machine Learning techniques such as linear regression, support vector regression, decision trees, and the Random Forrest Regressor are employed to forecast the value of stocks and characterise the behaviour of both buyers and sellers of assets.We projected the stock price using the day's ending value and the stock price.After evaluating the accuracy of each model and establishing which is the more effective algorithm to estimate stock price, an algorithm with exceptional precision is chosen.We cannot foretell share market conditions since it is a murky field, and the share marketplaces can never be predicted.This study, on the other hand, can complete the task fast and technically, and that is the major purpose of this essay.