Surf Canyon (www.SurfCanyon.com), the developer of the popular application that delivers real-time search personalization on Google, Bing and Yahoo!, proudly announces that yesterday it surpassed one million queries per day.
Oakland, CA (PRWEB), November 10, 2009 -- Surf Canyon, the developer of the popular application that delivers real-time search personalization on Google, Bing and Yahoo!, proudly announces that yesterday it surpassed one million queries per day.
"Crossing the million queries a day threshold is an impressive accomplishment," said Mike Cassidy, CEO of tour review site Ruba and co-founder of Direct Hit, a search engine that pioneered using user activity to affect relevancy. "Surf Canyon's real-time search personalization is an exciting innovation and their growth clearly indicates that user's are appreciating the value."
Moreover, in a sign of recognition from the search community, SIGIR, the Association for Computing Machinery's Special Interest Group on Information Retrieval, has decided to publish Surf Canyon's research. The paper, entitled "Demonstration of Improved Search Result Relevancy Using Real-Time Implicit Relevance Feedback: http://www.surfcanyon.com/SurfCanyonDemonstrationResearchPaper.pdf," was presented at the SIGIR conference in July. Using blind, control-group studies, the research demonstrates how real-time search personalization is able to improve relevancy, on top of the major search engines, by up to 40%.
"Surf Canyon's evaluation is done on an operational system with real users, and it gives a lot of insight into the benefits of real-time personalization," said Thorsten Joachims, Associate Professor of Computer Science at Cornell University. "This is a great paper and one of the most interesting, original and relevant IR papers I have read in a while!"
Surf Canyon operates with Google, Bing, Yahoo! and Craigslist. During a standard search, as the user makes selections, Surf Canyon's instantaneous relevancy algorithm determines what information is being sought and then re-ranks the results "on the fly," digging out pertinent documents from as deep as page 100.
###
