In its second-largest acquisition, Amazon buys the company for $970 million.
“Under” and $200” mean something different when the terms are combined than when expressed individually. IPhrase’s natural language processing technology figures it out to deliver more relevant search results.
Site search vendors are serving up technology that more closely mirrors human thought processes with every iteration, and for retailers, than can mean more sales. “We’ve focused on taking that customer interaction with search on a site and capitalizing on it to facilitate a business outcome,” says search and navigation technology vendor iPhrase Technologies’ Tony Frazier, senior vice president of marketing.
What iPhrase natural language processing-based technology does with a query on retailer site eLuxury.com is just one example. Under earlier-generation search technologies, a search for “earrings under $200" would likely return results containing any of the three terms, reflecting a broad range of relevancy – or not. NLP, however, “parses” the query, breaking it up into component parts to determine the meaning of each term individually and then in combination. That determines, for example, that “under $200” is a price constraint rather than two terms to be pulled individually into the search results.
Using NLP, iPhrase’s technology compares the individual and combined elements of the parsed query to what’s in the site’s searchable database, which includes category information, product information, brand names, longer merchandising descriptions, and more. “It takes what the user asks for and compares it against the different elements of back-end content,” says Frazier. That means results listings deliver a limited and more precise number of answers that get users to where they want to be faster, he says.
Frazier notes that retailers such as Neiman Marcus have seen as much as a 300% improvement in conversions of site search after implementing iPhrase’s search and navigation technology.