Investigation Into Machine Learning Models for Predicting Stock Price and Spread Movements From News Articles

8 Pages Posted: 30 Jun 2020

See all articles by Pontus Wistbacka

Pontus Wistbacka

Hanken School of Economics

Samuel Rönnqvist

Åbo Akademi University - Turku Centre for Computer Science (TUCS)

Katia Vozian

Hanken School of Economics - Helsinki Graduate School of Economics

Satchit Sagade

Goethe University Frankfurt - Department of Finance; Leibniz Institute for Financial Research SAFE

Date Written: May 29, 2020

Abstract

We explore several ways of using news articles and financial data to train neural network machine learning models to predict shock events in high-frequency market data, and aggregated shock episodes. We investigate the use of price movements in this context, and separately at a daily interval as well. We describe in detail how training sets are created from our data sources and how our machine learning models are trained. We find that pairing company-related news text with events or movements in financial time series proves less straight-forward than the literature would indicate. We discuss possible reasons for negative results, especially relating to the combination of minute-level news and millisecond-level market data.

Keywords: predictive models, machine learning, liquidity shock, high frequency trading, stock price

Suggested Citation

Wistbacka, Pontus and Rönnqvist, Samuel and Vozian, Katia and Sagade, Satchit, Investigation Into Machine Learning Models for Predicting Stock Price and Spread Movements From News Articles (May 29, 2020). Available at SSRN: https://ssrn.com/abstract=3619970 or http://dx.doi.org/10.2139/ssrn.3619970

Pontus Wistbacka (Contact Author)

Hanken School of Economics ( email )

PB 287
Helsinki, Vaasa 65101
Finland

Samuel Rönnqvist

Åbo Akademi University - Turku Centre for Computer Science (TUCS) ( email )

Joukahaisenkatu 3-5
Turku, 20520
Finland

Katia Vozian

Hanken School of Economics - Helsinki Graduate School of Economics

Helsinki
Finland

Satchit Sagade

Goethe University Frankfurt - Department of Finance ( email )

House of Finance
Theodor-W.-Adorno-Platz 3
Frankfurt am Main, Hessen 60323
Germany
+49 69 798 30085 (Phone)

Leibniz Institute for Financial Research SAFE ( email )

(http://www.safe-frankfurt.de)
Theodor-W.-Adorno-Platz 3
Frankfurt am Main, 60323
Germany
+49 69 798 30085 (Phone)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
87
Abstract Views
462
rank
348,814
PlumX Metrics