Behind Walmart’s miles of store shelves has always been a significant technology operation aimed at bringing efficiency to operations and delivering to customers what they want.
Increasingly, the world’s largest retailer must also compete for sales on desktop and mobile browsers. Today, it announced the completion of an in-house project to build a specialized search engine that boost purchases on its website.
The project, called Polaris, was built over ten months out of the company’s Silicon Valley research and technology office @WalmartLabs, which opened last year after Walmart acquired the search company Kosmix.
Walmart says that 10 to 15 percent more shoppers are completing transactions after searching Walmart.com using the new tool, which uses machine learning and text mining techniques to infer meaning and context from a query, rather than matching specific terms. For example, it understands a shopper means “jeans” if he types “denim” or that he might be interested in pool equipment if he queries “chlorine tablets.”
Reporting about the development of Walmart’s search tool in May, Reuters wrote that eBay and Google are also racing to improve e-commerce search results:
“The stakes have never been higher for whoever can deliver a high-quality shopping search experience for consumers,” said Etzioni, who has advised firms including Google and Microsoft.
All in all, focusing on search seems like a good move for Walmart, but to fully see the benefits, the company will have to bring shoppers to its site in the first place, rather than competitors’ such as Amazon.