Coupling News Sentiment with Web Browsing Data Improves Prediction of Intra-Day Price Dynamics

24 Pages Posted: 6 Dec 2015 Last revised: 16 Dec 2015

See all articles by Gabriele Ranco

Gabriele Ranco

IMT Institute for Advanced Studies

Ilaria Bordino

Yahoo! - Yahoo! Research Labs

Giacomo Bormetti

University of Bologna - Department of Mathematics

Guido Caldarelli

IMT Alti Studi Lucca

Fabrizio Lillo

Università di Bologna

Michele Treccani

List Group; QUANT Lab

Date Written: December 15, 2015

Abstract

The new digital revolution of big data is deeply changing our capability of understanding society and forecasting the outcome of many social and economic systems. Unfortunately, information can be very heterogeneous in the importance, relevance, and surprise it conveys, affecting severely the predictive power of semantic and statistical methods. Here we show that the aggregation of web users' behavior can be elicited to overcome this problem in a hard to predict complex system, namely the financial market. Specifically, our in-sample analysis shows that the combined use of sentiment analysis of news and browsing activity of users of Yahoo! Finance greatly helps forecasting intra-day and daily price changes of a set of 100 highly capitalized US stocks traded in the period 2012-2013. Sentiment analysis or browsing activity when taken alone have very small or no predictive power. Conversely, when considering a "news signal" where in a given time interval we compute the average sentiment of the clicked news, weighted by the number of clicks, we show that for nearly 50% of the companies such signal Granger-causes hourly price returns. Our result indicates a "wisdom-of-the-crowd" effect that allows to exploit users' activity to identify and weigh properly the relevant and surprising news, enhancing considerably the forecasting power of the news sentiment.

Keywords: financial markets, complex systems, data science, computational social science

Suggested Citation

Ranco, Gabriele and Bordino, Ilaria and Bormetti, Giacomo and Caldarelli, Guido and Lillo, Fabrizio and Treccani, Michele, Coupling News Sentiment with Web Browsing Data Improves Prediction of Intra-Day Price Dynamics (December 15, 2015). Available at SSRN: https://ssrn.com/abstract=2699167 or http://dx.doi.org/10.2139/ssrn.2699167

Gabriele Ranco (Contact Author)

IMT Institute for Advanced Studies ( email )

Complesso San Micheletto
Lucca, 55100
Italy

Ilaria Bordino

Yahoo! - Yahoo! Research Labs ( email )

Santa Clara, CA 95054
United States

Giacomo Bormetti

University of Bologna - Department of Mathematics ( email )

Piazza di Porta S. Donato , 5
Bologna, Bologna 40126
Italy

Guido Caldarelli

IMT Alti Studi Lucca ( email )

Piazza San Francesco 19
Lucca, 55100
Italy

Fabrizio Lillo

Università di Bologna ( email )

Via Zamboni, 33
Bologna, 40126
Italy

Michele Treccani

List Group ( email )

Via Pietrasantina 123
pisa, 56122
Italy

HOME PAGE: http://www.quantlab.it

QUANT Lab ( email )

Via Pietrasantina 123
Pisa, Pisa 56122
Italy

Register to save articles to
your library

Register

Paper statistics

Downloads
55
Abstract Views
476
rank
367,171
PlumX Metrics