Stock Market prediction using Regression Model based on Random Forest Method

Abstract

Prediction of Stock price is nowadays an existing and interesting research area in financial and academic sectors to know the scale of economies. No significant set of rules existed to estimate and predict the scale of shares in the stock exchange. Many evolutionary technologies are existing such as Technical, Fundamental, Statistical, and Time series analysis which help us to attempt the prediction process, but none of the methods are proven to be a reliable and accurate tool for society in the estimation of a Stock Exchange or Share Market scales. Here this paper attempted to do innovative work through the Machine Learning approach to predict or sense the behaviors tracking of the stock market Sensex, Nifty and HUL. Random Forest Regressor is the Machine Learning model implemented effectively in predicting the stock prices and defining the activity between the exchanges and the securities between the buyers and sellers. This paper predicts the price of the stock based on the closing price. In an algorithm with high accuracy, the process of comparison for the accuracy of each of the models and finally is considered a better algorithm for predicting stock price. As the share market is a vague domain, cannot predict the conditions that occur, and also share market can never be predicted, this job can be done easily and technically through this work and the main aim of this paper is to apply algorithms in Machine Learning in predicting the stock prices.

This research topic will always be important for investors who seek to generate excess returns, make buy-sell decisions, and determine portfolio allocation, particularly considering the development of machine learning techniques and algorithmic improvement. In an inefficient market, investors will have a difficult time achieving those ends because the market will be volatile. Volatility creates opportunities for making Gains and Losses, but it makes investors’ investment decision-making harder. This paper is contributing to this ongoing research on assessing stock market returns predictability and market efficiency. Even though belief predicting stock market returns with high accuracy using monthly returns is difficult, investors can still use the paper’s findings to help them guide their asset allocation and make buy-sell decisions.