Artificial intelligence for stock market price prediction

Abstract. Prediction of the stock market price is one of the most challenging tasks both for researchers and practitioners. One of the main components of the economy is financial markets, and their growth and development is a crucial and significant factor in the world. Meanwhile, artificial intelligence is an exponentially developing field. The use of artificial intelligence in financial markets is a new and intensely developing phenomenon, requiring extensive research. The aim of this paper is to present a set of methods applicable to stock market prediction. In order to show the differences two categories of methods were chosen: forecasting based on statistical methods and methods of artificial intelligence. The results of the research show that widely applied methods from the first group are based on Box-Jenkins methodology, e.g. ARMA, ARIMA methods, GARCH/ARCH methods. After analysis of methods of artificial intelligence, it can be identified as the most popular supervised learning algorithms like linear regression, decision trees/regression tree, random forest classification/ regression, and support vector machines.