Predicting the future with web search queries

Goel et al. find that online activity at any moment in time not only provides a snapshot of the instantaneous interests, concerns, and intentions of the global population, but it is also predictive of what people will do in the near future:

Recent work has demonstrated that Web search volume can “predict the present,” meaning that it can be used to accurately track outcomes such as unemployment levels, auto and home sales, and disease prevalence in near real time. Here we show that what consumers are searching for online can also predict their collective future behavior days or even weeks in advance. Specifically we use search query volume to forecast the opening weekend box-office revenue for feature films, first-month sales of video games, and the rank of songs on the Billboard Hot 100 chart, finding in all cases that search counts are highly predictive of future outcomes. We also find that search counts generally boost the performance of baseline models fit on other publicly available data, where the boost varies from modest to dramatic, depending on the application in question... We conclude that in the absence of other data sources, or where small improvements in predictive performance are material, search queries provide a useful guide to the near future.

And, in a similar vein, Preis et al. find a strong correlation between queries submitted to Google and weekly fluctuations in stock trading. They introduce a method for quantifying complex correlations in time series with which they find a clear tendency that search volume time series and transaction volume time series show recurring patterns. From the ScienceNow summary:

The Google data could not predict the weekly fluctuations in stock prices. However, the team found a strong correlation between Internet searches for a company's name and its trade volume, the total number of times the stock changed hands over a given week. So, for example, if lots of people were searching for computer manufacturer IBM one week, there would be a lot of trading of IBM stock the following week. But the Google data couldn't predict its price, which is determined by the ratio of shares that are bought and sold.

At least not yet. Neil Johnson, a physicist at the University of Miami in Florida, says that if researchers could drill down even farther into the Google Trends data—so that they could view changes in search terms on a daily or even an hourly basis—they might be able to predict a rise or fall in stock prices. They might even be able to forecast financial crises. It would be an opportunity for Google "to really collaborate with an academic group in a new area," he says. Then again, if the hourly stream of search queries really can predict stock price changes, Google might want to keep those data to itself.