KU study: Search data can predict stock returns

LAWRENCE, Kan. — Looking for a fresh place to collect stock tips? A University of Kansas research team suggests looking at data from online search engines.

The team says a large numbers of online searches for a particular stock can predict abnormal stock returns and trading volumes the subsequent week.

Associate marketing professor Kissan Joseph says there’s growing evidence in various disciplines that online search data can predict behavior.

He says the kind of data that can be retrieved from an engine like Google Insights for Search is a reliable predictor of stock returns and trading volumes, especially for volatile stocks whose true value is hard to gauge.

The university says in a news release that the team’s research utilizes S&P 500 firms over the period 2005-2008.