Hidden Treasures

February 18th, 2008

It has been observed for some time that search engine users rarely venture past the first page of results. Various studies have shown that only 10% of the time does a user click on a result with a rank greater than 10. A typical user would thus rather reformulate the query or abandon the search when they can’t find what they need on page one.

This is particularly problematic since, as discussed previously, it’s increasingly difficult, if not impossible, to map two- and three-word queries to the exploding content on the internet. It is thus increasing unlikely that the top 10 will contain the information sought without some form of additional input from the user, either explicitly (reformulation suggestions or clusters) or implicitly (personalization).

But what if there was a search technology that was able to dig into the results and fetch the relevant information for you?

Surf Canyon’s Discovery for Search™ technology is designed to find the “hidden treasures” in the subsequent search results, and Beta testing has confirmed this. The graph below compares the initial rank of a result (x-axis) with the frequency with which it is clicked (y-axis). The AOL data is from 2006 and the Surf Canyon data is from the most recent 10,000 queries. The result is that Surf Canyon doubles (17% vs. 9%) the users’ ability to find relevant information buried in the search results.


Tags: Discovery Personalization Research