Can Google queries help predict economic activity?
The answer depends on what you mean by "predict." Google Trends and Google Insights for Search provide a real time report on query volume, while economic data is typically released several days after the close of the month. Given this time lag, it is not implausible that Google queries in a category like "Automotive/Vehicle Shopping" during the first few weeks of March may help predict what actual March automotive sales will be like when the official data is released halfway through April.
That famous economist Yogi Berra once said "It's tough to make predictions, especially about the future." This inspired our approach: let us lower the bar and just try to predict the present.
Our work to date is summarized in a paper called Predicting the Present with Google Trends. We find that Google Trends data can help improve forecasts of the current level of activity for a number of different economic time series, including automobile sales, home sales, retail sales, and travel behavior.
Even predicting the present is useful, since it may help identify "turning points" in economic time series. If people start doing significantly more searches for "Real Estate Agents" in a certain location, it is tempting to think that house sales might increase in that area in the near future.
Our paper outlines one approach to short-term economic prediction, but we expect that there are several other interesting ideas out there. So we suggest that forecasting wannabes download some Google Trends data and try to relate it to other economic time series. If you find an interesting pattern, post your findings on a website and send a link to econ-forecast@google.com. We'll report on the most interesting results in a later blog post.
It has been said that if you put a million monkeys in front of a million computers, you would eventually produce an accurate economic forecast. Let's see how well that theory works ...
Posted 2nd April 2009 by Research Admin
Hal Varian, Google’s in-house economist, teaches us how to extract marketing insights from Google searches.
I recently asked a group of Googlers which day of the week had the most Google searches for the word ‘hangover.’ Most of them chose Sunday or Monday, although one party animal opted for Tuesday.
We can find the definitive answer – Sunday – by using a nifty tool called Google Insights for Search. This tool can be used to examine individual queries, but it can also compare search volumes for different queries. For example, searches for ‘vodka’ peak every Saturday, one day before the ‘hangover’ peak. The exception to this regular weekly pattern occurs once a year, on New Year’s Eve.
Searchblog’s John Battelle has called Google ‘the database of intentions,’ because search queries provide insights into people’s interests, intentions, and future actions. Needless to say, such insights can be very useful to businesses. Free tools like Google Correlate and Google Insights for Search enable you to use that database of intentions to ‘predict the present’ and better understand your customers’ behavior in real time.
“Free tools like Google Correlate and Google Insights for Search enable you to better understand your customers’ behavior in real time.”
For example, if you type ‘weight loss’ into Google Correlate you find ‘healthy smoothie’ and ‘meal replacement.’ Not too surprising. But you also see terms like ‘vacation destination,’ ‘cruises to,’ and ‘wedding checklist.’ And if you look at the searches that occur three weeks after the ‘weight loss’ query, you see ‘weight loss plateau’ and ‘not losing weight’ at the top of the list.
Using the publicly available tools mentioned above, we’ve uncovered a number of interesting relationships. Here are some examples.
- RETAIL
- When do ads take effect? By comparing Google AdWords data and MasterCard SpendingPulse data, we can see that people click on ads the most on Mondays. Online spending follows quickly – but not immediately – with online commerce peaking a day or two later. Offline spending patterns have a greater lag, trailing by one week.
- REAL ESTATE
- Reading the real estate market with Google Trends: As foreclosures started to rise and median house prices dropped, search queries in the real estate category were correlated to the number of new homes sold in the US.
No hay comentarios:
Publicar un comentario