Internet search data 'can predict markets'
Today's issue of the East Anglian Daily Times reports how Internet search data can be used to predict markets. According to the University of East Anglia and the University of Essex, investors can predict market movements by looking at the frequency of internet keyword searches.
According to the paper, researchers have analysed Google search frequency data for keywords related to 30 of the largest stocks traded on the New York Stock Exchange, including brands like Coca Cola, McDonalds, Microsoft, Procter & Gamble and Exxon Mobil. The report, published in the Journal of Banking and Finance, shows a 'strong association' between Google searches and stock return volatility and trading volume.
It's reported that this is the first evidence that online demand for information has a direct effect on all measures of stock market activity, a concept which has been under discussion for years. Dr Nikolaos Vlastakis, from Essex Business School, said 'We derived two new measures for information demand - one for the individual company and one for the whole market - and discovered that both have a strong association with stock return volatility and trading volume,' explains. 'Interestingly, we also found that the link between information demand and market activity becomes more prominent during turbulent times, such as the recent financial crisis.'
Professor Raphael Markellos from UEA's Norwich Business School is reported to have said that 'We explain this latter effect by showing that information demand is linked to investor attitudes towards risk. In periods such as the recent financial crisis, investors try harder than usual to reduce uncertainty by searching for information via Google.'