Conference article

Automated Stock Price Prediction Using Machine Learning

Mariam Moukalled
Computer Science Department, American University of Beirut, Lebanon

Wassim El-Hajj
Computer Science Department, American University of Beirut, Lebanon

Mohamad Jaber
Computer Science Department, American University of Beirut, Lebanon

Download article

Published in: Proceedings of the Second Financial Narrative Processing Workshop (FNP 2019), September 30, Turku Finland

Linköping Electronic Conference Proceedings 165:3, p. 16-24

NEALT Proceedings Series 40:3, p. 16-24

Show more +

Published: 2019-09-30

ISBN: 978-91-7929-997-2

ISSN: 1650-3686 (print), 1650-3740 (online)


Traditionally and in order to predict market movement investors used to analyze the stock prices and stock indicators in addition to the news related to these stocks; hence, the importance of news on the stock price movement. Most of the previous work in this industry focused on either labeling the released market news (positive, negative, neutral) and showings their effect on the stock price or focused on the historical prices movement and studied their future movement. In this work, we adopt a different approach that integrates both market news and stock prices in one model for the purpose of achieving better stock prediction accuracy. We propose an automated trading system that uses mathematical functions, machine learning, and other external factors such as news’ sentiments to issue profitable trades. Particularly, we aim to determine the price or the trend of a certain stock for the coming end-of-day considering the first n trading hours of the day. To achieve this goal, we trained traditional machine learning algorithms and also created and trained multiple deep learning models taking into consideration the importance of the relevant news. Various experiments were conducted, the highest accuracy (82.91%) of which was achieved using SVM for AAPL stock.


Stock Market Prediction, Machine Learning, Deep Learning


No references available

Citations in Crossref