EcommerceBytes-NewsFlash, Number 2395 - October 20, 2010     1 of 5

eBay to Overhaul Search Engine, Tests Are Rampant on Site

Email This Story to a Friend

eBay is working on a major re-engineering of its search engine. Code-named Cassini, the search engine will be much faster and more flexible, according to Hugh Williams, Vice President of Search Engineering, who came to eBay 18 months ago from Microsoft.

Over the next 12 months, eBay Inc. is launching a series of new search technologies and initiatives, designed to vastly improve user experiences at the company's sites, Williams said. This may have been what eBay CEO John Donahoe was referring to when he told an analyst in September that eBay needed 6 months to reach where it wanted to be with search.

Williams said machine-learned ranking would be introduced into search, meaning that the order of search results will be driven by more data factors than currently used. "In practice, this means the results will be more relevant to our users, and our search engine will adapt more easily, quickly and accurately to what our customers are doing on the site. We're already testing this on a small number of our users, and we're seeing great initial results."

eBay is always testing, Williams said - there are at least 50 new experiences on customers at any given time, with 15 different Best Match tests. "Most buyers are in at least one or two experiments, and typically don't notice. For example, right now, we have over 15 different search ranking algorithms on the U.S. site, a new crop of experiments to improve the speed of the site, and several tests of new merchandise placements.

You can read eBay's published interview with Williams in this October 13th press release.

About the author:

Ina Steiner is co-founder and Editor of EcommerceBytes and has been reporting on ecommerce since 1999. She's a widely cited authority on marketplace selling and is author of "Turn eBay Data Into Dollars" (McGraw-Hill 2006). Her blog was featured in the book, "Blogging Heroes" (Wiley 2008). Follow her on Twitter at @ecommercebytes and send news tips to

You may quote up to 50 words of any article on the condition that you attribute the article to and either link to the original article or to
All other use is prohibited.