Scientists suss out a correlation between certain Google searches and market moves.
Some big brains at Warwick Business School and Boston University have found that certain topics searched for on Google correlate, seem to prelude, shifts in the stock market.
According to the study--'Quantifying the semantics of search behavior before stock market moves,' published recently in the Proceedings of the National Academy of Sciences—humans have no chance of beating the stock market. The researchers point out that search engines record almost everything users search for. The records of these searches provide interesting fodder for study. The team quantified the meaning of every word on Wikipedia, categorized these words into topics, creating a computer-based meaning-system. Eventually they found that searches for terms relating to business and politics could be connected to subsequent stock market moves. Working through search data compiled between 2004 and 2012 the scientists found that, "No other topic was linked to returns that were significantly higher…Our results are in line with the hypothesis that increases in searches relating to both politics and business could be a sign of concern about the state of the economy, which may lead to decreased confidence in the value of stocks, resulting in transactions at lower prices."
Which is, perhaps, not that surprising. However, the researchers also found that the correlation is already diminishing. "Our analysis found that the strength of this relationship, using this very simple weekly trading strategy, has diminished in recent years.”
Why might this be? One suggestion was that computer-based trading strategies have already found the pattern and are arbitraging the correlation out of existence. Or as, the scientists put it, [the diminished correlation], “potentially reflects the increasing incorporation of Internet data into automated trading strategies, and highlights that more advanced strategies are now needed to fully exploit online data in financial trading." That is, you, mere human, have absolutely no chance of beating the market. Yet another argument for sticking to index funds, apparently.
According to the study--'Quantifying the semantics of search behavior before stock market moves,' published recently in the Proceedings of the National Academy of Sciences—humans have no chance of beating the stock market. The researchers point out that search engines record almost everything users search for. The records of these searches provide interesting fodder for study. The team quantified the meaning of every word on Wikipedia, categorized these words into topics, creating a computer-based meaning-system. Eventually they found that searches for terms relating to business and politics could be connected to subsequent stock market moves. Working through search data compiled between 2004 and 2012 the scientists found that, "No other topic was linked to returns that were significantly higher…Our results are in line with the hypothesis that increases in searches relating to both politics and business could be a sign of concern about the state of the economy, which may lead to decreased confidence in the value of stocks, resulting in transactions at lower prices."
Which is, perhaps, not that surprising. However, the researchers also found that the correlation is already diminishing. "Our analysis found that the strength of this relationship, using this very simple weekly trading strategy, has diminished in recent years.”
Why might this be? One suggestion was that computer-based trading strategies have already found the pattern and are arbitraging the correlation out of existence. Or as, the scientists put it, [the diminished correlation], “potentially reflects the increasing incorporation of Internet data into automated trading strategies, and highlights that more advanced strategies are now needed to fully exploit online data in financial trading." That is, you, mere human, have absolutely no chance of beating the market. Yet another argument for sticking to index funds, apparently.
