Detecting Causal Links between Financial News and Stocks

Haizhou Qu; Dimitar Lubomirov Kazakov

doi:10.1109/CIFEr.2019.8759058

Detecting Causal Links between Financial News and Stocks

Haizhou Qu, Dimitar Lubomirov Kazakov

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This article describes a novel framework for the detection of causal links between financial news and the subsequent movements of the stock market. The approach builds on and substantially improves a previously published in-house design for the detection and measurement of correlation between news and time series in the financial domain, which has been used here to detect a predictive causality relationship from news to prices and volumes of trade. While the original framework makes use of matrices of pairwise distances between companies, one based on news, the other - on financial performance, in order to produce a single measure of correlation between these two types of information for all traded companies, this article shows how the company contributing the most to the news-to-price/volume causal link can be singled out. The potential benefits of such information are made clear through its use in a straight-forward trading strategy, the results of which compare favourably to two strong, real-life alternatives that only make use of the time series.

Original language	English
Title of host publication	Proceedings of IEEE Conference on Computational Intelligence for Financial Engineering and Economics
Subtitle of host publication	(CIFEr 2019)
Place of Publication	Shenzhen, China
Publisher	IEEE
Pages	156-163
Number of pages	9
ISBN (Electronic)	978-1-7281-0033-3
ISBN (Print)	978-1-7281-0034-0
DOIs	https://doi.org/10.1109/CIFEr.2019.8759058
Publication status	Published - 11 Jul 2019
Event	2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics - Shenzhen, China Duration: 4 May 2019 → … http://www.ieee-cifer.org/website_cifer/about_2019.html

Publication series

Name	IEEE Symposium on Computational Intelligence for Financial Engineering and Economics
Publisher	IEEE
ISSN (Print)	2380-8454
ISSN (Electronic)	2640-7701

Conference

Conference	2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics
Abbreviated title	IEEE CIFEr 2019
Country/Territory	China
City	Shenzhen
Period	4/05/19 → …
Internet address	http://www.ieee-cifer.org/website_cifer/about_2019.html

Keywords

financial forecasting
financial news
stock prices
Granger causality

Access to Document

10.1109/CIFEr.2019.8759058

Detecting_Causal_Links_between_Financial_News_and_Stocks-1Accepted author manuscript, 364 KB

Cite this

@inproceedings{6638d11ebc9345c09455b5ff9a0a16b0,

title = "Detecting Causal Links between Financial News and Stocks",

abstract = "This article describes a novel framework for the detection of causal links between financial news and the subsequent movements of the stock market. The approach builds on and substantially improves a previously published in-house design for the detection and measurement of correlation between news and time series in the financial domain, which has been used here to detect a predictive causality relationship from news to prices and volumes of trade. While the original framework makes use of matrices of pairwise distances between companies, one based on news, the other - on financial performance, in order to produce a single measure of correlation between these two types of information for all traded companies, this article shows how the company contributing the most to the news-to-price/volume causal link can be singled out. The potential benefits of such information are made clear through its use in a straight-forward trading strategy, the results of which compare favourably to two strong, real-life alternatives that only make use of the time series.",

keywords = "financial forecasting, financial news, stock prices, Granger causality",

author = "Haizhou Qu and Kazakov, {Dimitar Lubomirov}",

year = "2019",

month = jul,

day = "11",

doi = "10.1109/CIFEr.2019.8759058",

language = "English",

isbn = "978-1-7281-0034-0",

series = "IEEE Symposium on Computational Intelligence for Financial Engineering and Economics",

publisher = "IEEE",

pages = "156--163",

booktitle = "Proceedings of IEEE Conference on Computational Intelligence for Financial Engineering and Economics",

address = "United States",

note = "2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics , IEEE CIFEr 2019 ; Conference date: 04-05-2019",

url = "http://www.ieee-cifer.org/website_cifer/about_2019.html",

}

Qu, H & Kazakov, DL 2019, Detecting Causal Links between Financial News and Stocks. in Proceedings of IEEE Conference on Computational Intelligence for Financial Engineering and Economics: (CIFEr 2019). IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, IEEE, Shenzhen, China, pp. 156-163, 2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics , Shenzhen, China, 4/05/19. https://doi.org/10.1109/CIFEr.2019.8759058

Detecting Causal Links between Financial News and Stocks. / Qu, Haizhou; Kazakov, Dimitar Lubomirov.

Proceedings of IEEE Conference on Computational Intelligence for Financial Engineering and Economics: (CIFEr 2019). Shenzhen, China : IEEE, 2019. p. 156-163 (IEEE Symposium on Computational Intelligence for Financial Engineering and Economics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Detecting Causal Links between Financial News and Stocks

AU - Qu, Haizhou

AU - Kazakov, Dimitar Lubomirov

PY - 2019/7/11

Y1 - 2019/7/11

N2 - This article describes a novel framework for the detection of causal links between financial news and the subsequent movements of the stock market. The approach builds on and substantially improves a previously published in-house design for the detection and measurement of correlation between news and time series in the financial domain, which has been used here to detect a predictive causality relationship from news to prices and volumes of trade. While the original framework makes use of matrices of pairwise distances between companies, one based on news, the other - on financial performance, in order to produce a single measure of correlation between these two types of information for all traded companies, this article shows how the company contributing the most to the news-to-price/volume causal link can be singled out. The potential benefits of such information are made clear through its use in a straight-forward trading strategy, the results of which compare favourably to two strong, real-life alternatives that only make use of the time series.

AB - This article describes a novel framework for the detection of causal links between financial news and the subsequent movements of the stock market. The approach builds on and substantially improves a previously published in-house design for the detection and measurement of correlation between news and time series in the financial domain, which has been used here to detect a predictive causality relationship from news to prices and volumes of trade. While the original framework makes use of matrices of pairwise distances between companies, one based on news, the other - on financial performance, in order to produce a single measure of correlation between these two types of information for all traded companies, this article shows how the company contributing the most to the news-to-price/volume causal link can be singled out. The potential benefits of such information are made clear through its use in a straight-forward trading strategy, the results of which compare favourably to two strong, real-life alternatives that only make use of the time series.

KW - financial forecasting

KW - financial news

KW - stock prices

KW - Granger causality

U2 - 10.1109/CIFEr.2019.8759058

DO - 10.1109/CIFEr.2019.8759058

M3 - Conference contribution

SN - 978-1-7281-0034-0

T3 - IEEE Symposium on Computational Intelligence for Financial Engineering and Economics

SP - 156

EP - 163

BT - Proceedings of IEEE Conference on Computational Intelligence for Financial Engineering and Economics

PB - IEEE

CY - Shenzhen, China

T2 - 2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics

Y2 - 4 May 2019

ER -