Deep Learning for Stock Market Prediction Using Sentiment and Technical Analysis

Georgios-Markos Chatziloizos, Dimitrios Gunopulos, Konstantinos Konstantinou

Abstract: Machine learning and deep learning techniques are applied by researchers with a background in both economics and computer science, to predict stock prices and trends. These techniques are particularly attractive as an alternative to existing models and methodologies because of their ability to extract abstract features from data. Most existing research approaches are based on using either numerical/economical data or textual/sentimental data. In this article, we use cutting-edge deep learning/machine learning approaches on both numerical/economical data and textual/sentimental data in order not only to predict stock market prices and trends based on combined data but also to understand how a stock's Technical Analysis can be strengthened by using Sentiment Analysis. Using the four tickers AAPL, GOOG, NVDA and S&P 500 Information Technology, we collected historical financial data and historical textual data and we used each type of data individually and in unison, to display in which case the results were more accurate and more profitable. We describe in detail how we analyzed each type of data, and how we used it to come up with our results.