Indonesian Journal of Electrical Engineering and Computer Science Vol. 16, No. 2, November 2019, pp. 1050~1058 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v16.i2.pp1050-1058  1050 Journal homepage: http://iaescore.com/journals/index.php/ijeecs Analytics of stock market prices based on machine learning algorithms Puteri Hasya Damia Abd Samad 1 , Sofianita Mutalib 2 , Shuzlina Abdul-Rahman 3 Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Malaysia Article Info ABSTRACT Article history: Received Jan 29, 2019 Revised Mar 2, 2019 Accepted May 13, 2019 This study focuses on the use of machine learning algorithms to analyse financial news on stock market prices. Stock market prediction is a challenging task because the market is known to be very volatile and dynamic. Investors face these kinds of problems as they do not properly understand which stock product to subscribe or when to sell the product with an optimum profit. Analyzing the information individually or manually is a tedious task as many aspects have to be considered. Five different companies from Bursa Malaysia namely CIMB, Sime Darby, Axiata, Maybank and Petronas were chosen in this study. Two sets of experiments were performed based on different data types. The first experiment employs textual data involving 6368 articles, extracted from financial news that have been classified into positive or negative using Support Vector Machine (SVM) algorithm. Bags of words and bags of combination words through Apriori algorithm are extracted as the features for the first experiment. The second experiment employs the numeric data type extracted from historical data involving 5321 records to predict whether the stock price is going up (positive) or down (negative) using Random Forest algorithm. The Rain Forest algorithm gives better accuracy in comparison with SVM algorithm with 99% and 68% accuracy respectively. The results demonstrate the complexities of the textual-based data and demand better feature extraction technique. Keywords: Bursa Malaysia Frequent itemset Machine learning Stock market prices prediction Text mining Copyright © 2019 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Sofianita Mutalib, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia. Email: sofi@tmsk.uitm.edu.my 1. INTRODUCTION Stock market investors normally have to make difficult decisions based on the assumptions that the presumed price is different from the current stock market price due to its intrinsic value [1-2]. The intrinsic value of the stock is considered as constant within a short period of time because opinions or decisions that have been made by investors are not expected to change drastically in a short period of time. Investors make comparisons between the perceived intrinsic value and its market value, and later investors make decisions on buying or selling or holding based on the current situation [2-3]. Billions of money are traded or exchanged every day whereby the investors are hoping that they will make profit instead of losses. Behavior of investors can affect stock prices, and investors influence stock prices by using information that are available in the public domain to predict the results of how the market will react [4-5]. This makes stock market analytics an extremely interesting area and its development is worthwhile for the investors. Market prediction that is effective might help the investors in terms of trading advice or as a key component for stockbrokers. Furthermore, prediction models can help investors in providing helpful information like market