In a new white paper just released, Google reveals how its working to predict future search trends.
I’m not a mathematician, so appreciated this basic summary:
For each trends sequence of interest, we take a point in time, t, which is about a year back, compute a one year forecasting for t based on historical data available at time t, and compare it to the actual trends sequence that occurs since time t. The error between the forecasting trends and the actual trends characterizes the predictability level of a sequence, and when the error is smaller than a pre-defined threshold, we denote the trends query as predictable.
Piece of cake!
Some of the findings include:
- 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%).
And, as the chart below demonstrates, Google’s margin of error stays pretty consistent even when making predictions 9 months out!
Go ahead and leave a comment with your thoughts on the paper–I predict a few of you will.