eBay patented a method for search based on diversity to help overcome a major challenge shopping sites face in serving up relevant listings in search results. The system it described "calculates a diversity index for a result set comprising results for a query."
(Note: this is not about the diversity of eBay's workforce, for example - this is about showing shoppers diverse items in search results.)
"Information retrieval relates to the searching of information stored on computing systems, such as searches for web pages, items for sale, documents, and images. To locate particular information, a user specifies a query about the information of interest and a search engine, for example, uses this query in the search. For example, online shopping and auction websites provide a number of publishing, listing, and price-setting mechanisms whereby a seller may list (or publish information concerning) items for sale. A buyer can express interest in or indicate a desire to purchase such items by, for example, submitting a query to the website for use in a search of the requested items.
"The accurate matching of a query to relevant items is currently a major technical challenge in the field of information retrieval. An example of such a challenge is that item descriptions (e.g., title) tend to be short and such descriptions may be uniquely defined by the sellers. The buyers seeking to purchase the items might use a different vocabulary from the vocabulary used by the sellers to describe the items. As an example, an item identified in the title as a "garnet" does not match a query "January birthstone" submitted by a buyer, although garnet s known as the birthstone for January. In another example, an item identified in the title as "Martin guitar" does not match the query "acoustic guitar" submitted by a buyer, although the Martin guitar is a type of an acoustic guitar. As a result, for example, online shopping and auction websites that use a conventional search engine to locate items may not effectively connect the buyers to the sellers."
The example of "garnet" not matching "January birthstone" jumped out at me. In 2008, I had interviewed Jamie Iannone
, who was then eBay Vice President of Global Search, and he had used that very example in talking about eBay's search engine.
It's interesting to look back at what eBay was thinking about search 11 years ago. At the time, Best Match sort was fairly new, and Iannone revealed four factors that influenced Best Match: Item Information - including category, title, attribute, and information about listings; Seller Information - including seller DSR scores, and other bad seller metrics; Demand Data - what are buyers doing on the site; and "Time Ending Soonest."
Now that eBay has moved to 30-day GTC, Time Ending Soonest is a quaint notion!
Do you find that eBay does a good job of finding items like garnets when people search January birthstone?