High frequency financial time series prediction: machine learning approach

Abstract

Machine learning is a rapidly evolving subfield of computer science. It has enormous amount of applications. One of the application domains is financial data analysis. Machine learning was usually applied for analysis and forecasting of daily financial time series. Availability of high frequency financial data became another challenge with its own specifics and difficulties. Regressors, being a significant part of machine learning field, have been selected as study subjects for this project. The purpose of this research is to apply machine learning techniques for predicting high frequency financial time series. Experiments are conducted using several regressors which are evaluated with respect to prediction quality and computation cost. The obtained results were analysed in order to reveal parameter combination for particular regressor that yields the best results according to chosen performance criteria.