Machine Learning Application in the Financial Markets Industry

Abstract

Machine Learning is increasingly prevalent in Stock Market trading. The goal of this paper is to investigate whether the machine learning technique is able to retrieve information from past prices and predict price movement and future trends. We explore using trend trading indicators in a machine learning based model. We propose algorithms that combine different technical and fundamental indicators in order to provide accurate positive indicators for stock price movements. In this paper, machine learning techniques such as the Logistic Regression, Decision Tree, Neural Networks and Artificial Intelligence are applied to big data from the stock market that is of high volume, high velocity, high variety and high variability using real time and off-line data of different time granularities.

The results of predictive algorithmswereanalysed and the results presented. Experimental results confirmed that the use of machine learning and artificial intelligence methods can help to select top performing stock portfolios that outperform the stock market.