Tampere University of Technology

TUTCRIS Research Portal

Forecasting stock prices from limit order book using convolutional neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication19th IEEE International Conference on Business Informatics
Subtitle of host publicationThessaloniki, Greece, 24-27 July 2017
PublisherIEEE
ISBN (Electronic)978-1-5386-3035-8
DOIs
Publication statusPublished - 2017
Publication typeA4 Article in a conference publication
EventIEEE International Conference on Business Informatics -
Duration: 1 Jan 1900 → …

Conference

ConferenceIEEE International Conference on Business Informatics
Period1/01/00 → …

Abstract

In today's financial markets, where most trades are performed in their entirety by electronic means and the largest fraction of them is completely automated, an opportunity has risen from analyzing this vast amount of transactions. Since all the transactions are recorded in great detail, investors can analyze all the generated data and detect repeated patterns of the price movements. Being able to detect them in advance, allows them to take profitable positions or avoid anomalous events in the financial markets. In this work we proposed a deep learning methodology, based on Convolutional Neural Networks (CNNs), that predicts the price movements of stocks, using as input large-scale, high-frequency time-series derived from the order book of financial exchanges. The dataset that we use contains more than 4 million limit order events and our comparison with other methods, like Multilayer Neural Networks and Support Vector Machines, shows that CNNs are better suited for this kind of task.

Publication forum classification