Performance Analysis of Regression Based Machine Learning Techniques for Prediction of Stock Market Movement
Nitin Nandkumar Sakhare1, S. Sagar Imambi2

1Nitin Nandkumar Sakhare, Research Scholar, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur (Andhra Pradesh), India.
2Dr. S. Sagar Imambi, Associate Professor, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur (Andhra Pradesh), India.
Manuscript received on 23 April 2019 | Revised Manuscript received on 05 May 2019 | Manuscript Published on 17 May 2019 | PP: 206-213 | Volume-7 Issue-6S4 April 2019 | Retrieval Number: F10400476S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Prediction of stock market movement is extremely difficult due to its high mutable nature. The rapid ups and downs occur in stock market because of impact from foreign commodities like emotional behavior of investors, political, psychological and economical factors. Continuous unsettlement in the stock market is major reason why investors sell out at the wrong time and often fail to gain the benefit. While investing in stock market investors must not forget the risk of reward rule and expose their holdings to greater risks. Although it is not possible predict stock market movement with full accuracy, losses from selling stocks at wrong time and its impacts can be reduce to greater extent using prediction of stock market movement based on analysis of historical data. Investors always need accurate predictions and they should use stock information wisely. A great quantity of chronological data is available in the context of stock market behavior. For stock market movement prediction, a number of machine learning algorithms are available. Use of particular machine learning algorithm has huge impact on prediction results obtained. In this paper, we have compared three different machine learning algorithms, namely, Linear Regression, Polynomial Regression and Support Vector Regression. We have applied stated techniques on data consisted of index and stock prices of S&P 500.
Keywords: Prediction; Stock Market; Machine Learning; Regression; Index; Stock Prices.
Scope of the Article: Machine Learning