Many new search technologies are working to solve this problem, including clustering, personalization, tagging, voting, social networking, natural language processing as well as meta-search, new visualization techniques and others. All of these techniques deliver value to the user; however, they look at the results page as the final, static product. Once produced and delivered, the onus is still upon the user to dig, potentially find something useful and, if unsuccessful, reformulate the query.

Surf Canyon is changing this approach by making the result set dynamic. The first presentation of results might very well have been the best "guess" given the knowledge that was available at the time the user executed the search. Nevertheless, as soon as the user takes his or her first action, that presentation quickly becomes obsolete.

By observing the user's behavior as the search is taking place, Surf Canyon's technology builds a real-time model of inferred intent, which is then used to calculate the "instantaneous relevancies" of documents in the result set. The instantaneous relevancies are then used to immediately move forward the most pertinent documents while pushing back those that are less relevant.

Surf Canyon transforms search from a lecture to a conversation.

Searchers who use Surf Canyon's Discovery Engine for Search while searching on Google or Yahoo! will be able to more quickly and easily find relevant information buried in the search results, significantly accelerating the search process.

Surf Canyon wrote a research paper that contains quantitative evaluations of our technology. Compared to a control sample without Surf Canyon's technology, we demonstrate 30% to 100% improvements in the ability of search engine users to find the information they want. Here is the full paper (pdf): Demonstration of Improved Search Result Relevancy Using Real-Time Implicit Relevance Feedback.