According to the research, Quantifying Trading Behavior in Financial Markets, mining Google search terms related to finance and using the data into an investment strategy would have outperformed all pickers over an eight year period ending in 2011. The report was made by big data academics and published in the journal Nature.
The academics, Professor Tobias Preis of Warwick Business School and Helen Susannah Moat of Boston University, have already made a stir by using similar approaches to quantify stock price in fluctuations of companies on the Standard & Poor’s 500 Index as well as the gross domestic product growth of the world’s largest countries. Their latest attempt is their controversial so far. They analyzed changes in the frequency of 98 general fiancé terms such as unemployment, credit, revenue, and Nasdaq in Google searches from 2004 to 2011. They then used the search volume data to come out with an investment strategy they named Google Trends Strategy. The result saw a market beating return over the period.
The team looked at the week-by-week basis the ups and downs of Google search volume for the search terms. Based on the results, the team would buy or sell its theoretical Dow Jones industrial average portfolio. If the search terms went up, they would sell in the following week. If there was a decrease, then they would buy.
With the strategy, the team got 326 percent return when analyzing the keyword debt. Other search terms got lower results. In contrast, a conservative buy-and-hold strategy that ignored Google searches got a return of 16 percent over the same period.
Preis said the findings got the attention of the finance industry. It could lead to a change in their investment strategies or algorithms. Moat said that online search data could give them new insight on how humans collect information before making decisions.