Title: Walking down Wall Street with a tablet: A survey of stock market predictions using the web
Citation: JOURNAL OF ECONOMIC SURVEYS vol. 30 no. 2 p. 356-369
Publication Year: 2016
JRC N°: JRC88003
ISSN: 0950-0804
URI: http://onlinelibrary.wiley.com/doi/10.1111/joes.12102/full
DOI: 10.1111/joes.12102
Type: Articles in periodicals and books
Abstract: A blindfold chimpanzee throwing darts at the Wall Street journal could select a portfolio that would do as well as the (stock market) experts (Mankiel 2003). But what if this chimpanzee could peek into internet beforehand? Has web information flow an influence on real stock market behavior? Stated differently: can a measure of financial news obtained from the web be useful in predicting the short term behavior of the stock market? We walk along this avenue of research by reviewing the link between stock market prices and web mining for financial information. The recent literature is abundant and increasing but findings are mixed. We concentrate our attention to the short term (days or at most weeks) as when repetitive and exploitable patterns are discovered in the stock market, most likely they will be arbitraged away and eventually disappear. We touch upon sentiment analysis and machine learning and we offer suggestions for future research.
JRC Directorate:Space, Security and Migration

Files in This Item:
There are no files associated with this item.

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.