Stock Prediction using Machine Learning Algorithms Komal 1 , Dr. S.C. Gupta 2 , Mr. Shekhar Singh 3 and Dr. Deepak Kumar 4 1-4 Department of Computer Science Engineering, P.I.E.T, Samalkha, Panipat Email: komalwadhwa2212@gmail.com, Hod.cse@piet.co.in, shekhar.cse@piet.co.in, Deepak.cse@piet.co.in Abstract— Every day more than 5000 trade companies enlisted in Bombay stock Exchange (BSE) offer an average of 24,00,00,000+ stocks, making an approximate of 2000Cr+ Indian rupees in investments. Thus analyzing such a huge market will prove beneficial to all stakeholders of the system. An application which focuses on the patterns generated in this stock trade over the period of time, and extracting the knowledge from those patterns to predict future behavior of the BSE stock market is essential. An application representing the information in visual form for user interpretation to buy and to sell a specific company’s stock is a key requirement. Such an application based on machine learning algorithms is the right choice in current scenario. This paper surveys the machine learning algorithms suitable for such an application; as well it discusses what are the current tools and techniques appropriate for its implementation. Index Terms— Support Vector Machine (SVM), Support Vector Regression (SVR) and stock market. I. INTRODUCTION Machine learning can be defined as the data which is obtained by knowledge extraction. Machines don’t have to be programmed explicitly instead they are trained to make decisions that are driven by data. Instead of writing a code for every specific problem, data is provided to the generic algorithms and logic is developed on the basis of that data. When a machine improves its performance based on its past experiences it can be said that machine has truly learnt. The technique for most accurate prediction is by learning from past instances, and to make a program to do this is best possible with machine learning techniques. Any machine learning technique (supervised or unsupervised) is efficient enough to generate rules for programs, in consideration with present ones to take a better decision. In this scenario, the decision is whether the stock will increase or decrease (Stock analysis). A stock market is an open market for companies or for individuals to raise money. Stock market helps companies to purchase or sell their shares. The cost of shares relies on the interest and supplies of shares. This procedure of purchasing and selling of shares is called trading/exchanging; just the Listed Companies are permitted to do exchanging. Recently huge amounts of investment are exchanged via stock market over the world. National economies are firmly connected and intensely affected the execution of their Stock Markets. Therefore they are identified with macroeconomic parameters, as well as they impact ordinary life in a more straightforward manner. Hence they constitute a mechanism which has vital and immediate social effects. The nature of stock market in common is unpredictable which may depend on the long and short term future state. This is unpleasant and also unavoidable for the speculator when Stock Market is chosen as an investment tool. The main aim is to reduce this unpredictability and the Stock Market Anticipation (or Forecasting) is used Grenze ID: 01.GIJET.8.1.128 © Grenze Scientific Society, 2022 Grenze International Journal of Engineering and Technology, Jan Issue