Stock Market Prices Prediction using Random Forest and Extra Tree Regression

Abstract

Prediction of Stock price is now a day’s an existing and interesting research area in financial and academic sectors to know the scale of economies. There did not exists any significant set of rules to estimate and predict the scale of share in the stock exchange. Many evolutionary technologies are existing such as technical, fundamental, time, statistical and series analysis which help us to attempt the prediction process, but none of the methods are proved as reliable and accurate tool to the society in the estimation of stock exchange or share market scales. Here in this paper we attempted to do innovative work through Machine Learning approach to predict or sense the behaviour tracking of the stock market sensex. Linear regression, Support Vector regression, Decision Tree, Ramdom Forest Regressor and Extra Tree Regressor are the Machine Learning models implemented effectively in predicting the stock prices and define the activity between the exchanges the securities between the buyers and sellers. We predicted the price of the stock based on the closing value and stock price. An algorithm with high accuracy we do the process of comparison for the accuracy of each of the model and finally is considered as better algorithm for predicting stock price. As share market is a vague domain we cannot predict the conditions 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.

Comparing Long Short-Term Memory and Random Forest Accuracy for Bitcoin Price Forecasting

“…In terms of computational speed and power, there are reasons why Random Forest (RF) may be faster at performing calculations to predict Bitcoin prices compared to Long Short-Term Memory (LSTM). The Random Forest algorithm is based on a collection of relatively simple decision trees [32], whereas LSTM involves a more complex neural network with multiple layers and more complicated connections [33]. Computations in RF usually involve making simple decisions on each tree, which may take less time Ì 269 than LSTMs and have to go through many layers of neurons and more complicated mathematical computations.…”

Random forest model for forecasting vegetable prices: a case study in Nakhon Si Thammarat Province, Thailand

“…Random forest constructs numerous versions of These tree predictions are combined with a majority vote to get the final projection. As a consequence, over-fitting is reduced, and predicted accuracy is improved [27]. An overview of how the algorithms work is depicted in Figure 2.…”

An Efficient Stock Price Prediction Mechanism Using Multivariate Sequential LSTM Autoencoder

“…Khaidem et al [2] used a random forest algorithm to predict the direction of stock market prices, achieving an accuracy for some stocks to about 85-90%. Polamuri et al [1] presented a methodology for predicting stock prices using random forest and extra tree regressions algorithms. The authors conclude that machine learning algorithms can be used for estimating the prices of stocks.…”

“…Khaidem et al [2] used the algorithm to achieve an accuracy of 85-90% for predicting the direction of stock market prices. Polamuri et al [1] presented a methodology for predicting stock prices using the random forest and extra tree regressions algorithms. Kumar et al [13] found that the random forest algorithm achieved the highest prediction accuracy among several supervised machine learning algorithms, including decision trees and support vector machines, for larger datasets.…”