Correlating financial time series with micro-blogging activity

Eduardo J. Ruiz, Vagelis Hristidis, Carlos Castillo, Aristides Gionis, Alejandro Jaimes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

142 Citations (Scopus)

Abstract

We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks. Specifically, we collect messages related to a number of companies, and we search for correlations between stock-market events for those companies and features extracted from the microblogging messages. The features we extract can be categorized in two groups. Features in the first group measure the overall activity in the micro-blogging platform, such as number of posts, number of re-posts, and so on. Features in the second group measure properties of an induced interaction graph, for instance, the number of connected components, statistics on the degree distribution, and other graph-based properties. We present detailed experimental results measuring the correlation of the stock market events with these features, using Twitter as a data source. Our results show that the most correlated features are the number of connected components and the number of nodes of the interaction graph. The correlation is stronger with the traded volume than with the price of the stock. However, by using a simulator we show that even relatively small correlations between price and micro-blogging features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.

Original languageEnglish
Title of host publicationWSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining
Pages513-521
Number of pages9
DOIs
Publication statusPublished - 15 Mar 2012
Externally publishedYes
Event5th ACM International Conference on Web Search and Data Mining, WSDM 2012 - Seattle, WA, United States
Duration: 8 Feb 201212 Feb 2012

Other

Other5th ACM International Conference on Web Search and Data Mining, WSDM 2012
CountryUnited States
CitySeattle, WA
Period8/2/1212/2/12

Fingerprint

Time series
Industry
Simulators
Statistics
Financial markets

Keywords

  • Financial time series
  • Micro-blogging
  • Social networks

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Ruiz, E. J., Hristidis, V., Castillo, C., Gionis, A., & Jaimes, A. (2012). Correlating financial time series with micro-blogging activity. In WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining (pp. 513-521) https://doi.org/10.1145/2124295.2124358

Correlating financial time series with micro-blogging activity. / Ruiz, Eduardo J.; Hristidis, Vagelis; Castillo, Carlos; Gionis, Aristides; Jaimes, Alejandro.

WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. p. 513-521.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ruiz, EJ, Hristidis, V, Castillo, C, Gionis, A & Jaimes, A 2012, Correlating financial time series with micro-blogging activity. in WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. pp. 513-521, 5th ACM International Conference on Web Search and Data Mining, WSDM 2012, Seattle, WA, United States, 8/2/12. https://doi.org/10.1145/2124295.2124358
Ruiz EJ, Hristidis V, Castillo C, Gionis A, Jaimes A. Correlating financial time series with micro-blogging activity. In WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. p. 513-521 https://doi.org/10.1145/2124295.2124358
Ruiz, Eduardo J. ; Hristidis, Vagelis ; Castillo, Carlos ; Gionis, Aristides ; Jaimes, Alejandro. / Correlating financial time series with micro-blogging activity. WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. pp. 513-521
@inproceedings{727c4d3d2158485597bccedea2298739,
title = "Correlating financial time series with micro-blogging activity",
abstract = "We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks. Specifically, we collect messages related to a number of companies, and we search for correlations between stock-market events for those companies and features extracted from the microblogging messages. The features we extract can be categorized in two groups. Features in the first group measure the overall activity in the micro-blogging platform, such as number of posts, number of re-posts, and so on. Features in the second group measure properties of an induced interaction graph, for instance, the number of connected components, statistics on the degree distribution, and other graph-based properties. We present detailed experimental results measuring the correlation of the stock market events with these features, using Twitter as a data source. Our results show that the most correlated features are the number of connected components and the number of nodes of the interaction graph. The correlation is stronger with the traded volume than with the price of the stock. However, by using a simulator we show that even relatively small correlations between price and micro-blogging features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.",
keywords = "Financial time series, Micro-blogging, Social networks",
author = "Ruiz, {Eduardo J.} and Vagelis Hristidis and Carlos Castillo and Aristides Gionis and Alejandro Jaimes",
year = "2012",
month = "3",
day = "15",
doi = "10.1145/2124295.2124358",
language = "English",
isbn = "9781450307475",
pages = "513--521",
booktitle = "WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining",

}

TY - GEN

T1 - Correlating financial time series with micro-blogging activity

AU - Ruiz, Eduardo J.

AU - Hristidis, Vagelis

AU - Castillo, Carlos

AU - Gionis, Aristides

AU - Jaimes, Alejandro

PY - 2012/3/15

Y1 - 2012/3/15

N2 - We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks. Specifically, we collect messages related to a number of companies, and we search for correlations between stock-market events for those companies and features extracted from the microblogging messages. The features we extract can be categorized in two groups. Features in the first group measure the overall activity in the micro-blogging platform, such as number of posts, number of re-posts, and so on. Features in the second group measure properties of an induced interaction graph, for instance, the number of connected components, statistics on the degree distribution, and other graph-based properties. We present detailed experimental results measuring the correlation of the stock market events with these features, using Twitter as a data source. Our results show that the most correlated features are the number of connected components and the number of nodes of the interaction graph. The correlation is stronger with the traded volume than with the price of the stock. However, by using a simulator we show that even relatively small correlations between price and micro-blogging features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.

AB - We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks. Specifically, we collect messages related to a number of companies, and we search for correlations between stock-market events for those companies and features extracted from the microblogging messages. The features we extract can be categorized in two groups. Features in the first group measure the overall activity in the micro-blogging platform, such as number of posts, number of re-posts, and so on. Features in the second group measure properties of an induced interaction graph, for instance, the number of connected components, statistics on the degree distribution, and other graph-based properties. We present detailed experimental results measuring the correlation of the stock market events with these features, using Twitter as a data source. Our results show that the most correlated features are the number of connected components and the number of nodes of the interaction graph. The correlation is stronger with the traded volume than with the price of the stock. However, by using a simulator we show that even relatively small correlations between price and micro-blogging features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.

KW - Financial time series

KW - Micro-blogging

KW - Social networks

UR - http://www.scopus.com/inward/record.url?scp=84858020958&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858020958&partnerID=8YFLogxK

U2 - 10.1145/2124295.2124358

DO - 10.1145/2124295.2124358

M3 - Conference contribution

SN - 9781450307475

SP - 513

EP - 521

BT - WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining

ER -