BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20151025T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20160327T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.7229.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260403T175708Z
CREATED:20160115T072921Z
DESCRIPTION:With Internet provision becoming ubiquitous\, people have been 
 increasingly turning to search engines\, micro-blogging platforms\, questi
 ons/answering forums\, and online encyclopedias for news\, information and
  research purposes.The massive corpus of people’s digital actions can be v
 iewed at any moment in time as a snapshot of their collective consciousnes
 s\, reflecting their instantaneous interests\, concerns\, and intentions\,
  and thus opening up new opportunities for a more precise and extensive qu
 antification of real-world phenomena\, including politic\, economic and so
 cial events and trends. A special case of interest is the financial domain
 \, where gathering information on people’s intentions before trading decis
 ions were taken and revealing early signs of events (like stock market mov
 es) may have paramount importance in presence of financial crises or other
  catastrophic events that result from a combination of actions\, and affec
 t humans worldwide.In this talk I will present my research on tracking tra
 ding volumes and price returns of highly treaded stocks based on search qu
 eries\, browsing activity on financial portals\, and sentiment analysis of
  related news.  My work was based on the analysis of massive-scale logs pr
 ovided by Yahoo. Results show that daily trading volumes of stocks traded 
 in NASDAQ-100 are correlated with daily volumes of queries related to the 
 same stocks. Web browsing on Yahoo Finance results in a higher predictive 
 power than regular web searches\, being able to anticipate stock trading v
 olumes by two or three days. Finally\,  the combined use of sentiment anal
 ysis of news and browsing activity of users of Yahoo! Finance allows to fo
 recast intra-day and daily price changes\, thanks to a wisdom-of-crowds ef
 fect 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.Bio. Dr. Ilaria Bordino got  her PhD in Compu
 ter Engineering in 2010 from Sapienza University of Rome and Pompeu Fabra 
 University of Barcelona\, and is currently a Researcher at UniCredit R&D w
 here she works on designing graph-based algorithms for the analysis of fin
 ancial networks and credit risk assessment\, and on natural language proce
 ssing tools for online reputation management and information extraction fr
 om unstructured text. Prior to joining UniCredit\, Ilaria was a visiting R
 esearcher at Max Planck Institute for Informatics in Saarbruecken\, German
 y (Fall 2010)\, where she designed a graph-based algorithm for named-entit
 y disambiguation\, and then a Research Scientist at Yahoo Labs in Barcelon
 a (February 2011 - June 2015)\, where she worked on web information retrie
 val and big data mining\, user behavior analysis\, complex networks\, soci
 al networks. While at Yahoo\, Ilaria participated in the European Project 
 FOC (http://www.focproject.eu)\, aimed at anticipating structural instabil
 ities in global financial networks\, and in the LiMoSINe Project (http://l
 imosine-project.eu)\, aimed to develop a new truly semantic aggregation pa
 radigm for search engines\, enabling semantically structural access to mul
 ti-lingual online content. Ilaria has published her work at premier confer
 ences such as SIGIR\, WSDM\, CIKM\, WWW\, EMNLP and ICDM. She also has bee
 n serving on the program committee of top tier conferences and journals in
  the areas of Data Mining and Information Retrieval.
DTSTART;TZID=Europe/Paris:20160120T120000
DTEND;TZID=Europe/Paris:20160120T120000
LAST-MODIFIED:20190805T155749Z
LOCATION:DIAG\, via Ariosto 25 - Aula Magna I floor
SUMMARY:Tracking financial trends with Yahoo users’ searching and browsing 
 behavior - Ilaria Bordino
URL;TYPE=URI:http://www.diag.uniroma1.it/node/7229
END:VEVENT
END:VCALENDAR