A team of researchers from the UK and US have used a large set of Google Trends data to uncover early warning signs of stockmarket moves.
In a paper published in the journal Scientific Reports today, Tobias Preis of Warwick Business School, Helen Susannah Moat of University College London, and H. Eugene Stanley of Boston University argue it is possible to use big data to predict market behaviour.
The researchers analysed historical Google Trends data between 2004 and 2011, focusing on 98 search terms related to finance, debt and stock markets. They found prior to drops in the financial market, investors searched for more information about the market.
“These results further illustrate the exciting possibilities offered by new big data sets to advance our understanding of complex collective behavior in our society,” the researchers write.
They go further to argue the warning signs in search volume data could be used to construct profitable trading strategies, with an analysis of searches for the word “debt” helping to yield a potential profit of 326 percent in a model portfolio.
The work was supported by the US Government’s Intelligence Advanced Research Projects Activity (IARPA), which claims to invest in “high-risk, high-payoff research programs that have the potential to provide the United States with an overwhelming intelligence advantage over future adversaries”.
IARPA's Open Source Indicators Program aims to develop methods for continuous, automated analysis of publicly available data in order to anticipate significant societal events, such as political crises, disease outbreaks, and economic instability.