Google Knows

For about a couple of months now I have been thinking about the kind of money I'd make (it'd be big!) if I could predict the keywords that would trend in Google Search two or three months to the future. I know that it's possible, one only needs to study for some time the keywords that people google, find some pattern in there that would help predict what keywords would be searched most in the future. Well, I did not know that Google has been working on this kind of thing and now they have a white paper entitled On the Predictability of Search Trends which you can download in PDF. Here are some of Google's findings about their study:

# Over half of the most popular Google search queries are predictable in a 12 month ahead forecast, with a mean absolute prediction error of about 12%.
# Nearly half of the most popular queries are not predictable (with respect to the model we have used).
# Some categories have particularly high fraction of predictable queries; for instance, Health (74%), Food & Drink (67%) and Travel (65%).
# Some categories have particularly low fraction of predictable queries; for instance, Entertainment (35%) and Social Networks & Online Communities (27%).
# The trends of aggregated queries per categories are much more predictable: 88% of the aggregated category search trends of over 600 categories in Insights for Search are predictable, with a mean absolute prediction error of of less than 6%.
# There is a clear association between the existence of seasonality patterns and higher predictability, as well as an association between high levels of outliers and lower predictability. For the Entertainment category that has typically less seasonal search behavior as well as relatively higher number of singular spikes of interest, we have seen a predictability of 35%, where as the category of Travel with a very seasonal behavior and lower tendency for short spikes of interest had a predictability of 65%.
# One should expect the actual search trends to deviate from forecast for many predictable queries, due to possible events and dynamic circumstances.
# We show the forecasting vs actual for trends of a few categories, including some that were used recently for predicting the present of various economic indicators. This demonstrates how forecasting can serve as a good baseline for identifying interesting deviations in actual search traffic.

And this is the sweetest news: Google is introducing today a new forecasting feature in Insights for Search, along with a new version of the product. If you are wondering why I am saying that this is sweet news, well, you need to understand that keywords are the reason why I and my wife earn an average of $1,000 a month from Adsense. If we can see in advance what keywords will trend when, then we can plan ahead and do steps now to get the best out of what is coming. I heard from a reliable source that a Filipino Blogger made around $3,000 in one day from Adsense because he predicted the keywords that would trend during a particular date, one month in advance.

Labels: ,