Google Builds from for Shoppers

Google Nov. 17 opened the online doors to shopping comparison Website, which helps people find and buy clothes and shoes online based on curated preferences.

Google Nov. 17 launched, a shopping comparison Website that leverages machine learning and computer vision to help users find and buy clothes and shoes online.

Google, which timed the launch before Black Friday kicks off Nov. 26, argued that people shop for such products differently than they do for hard goods such as consumer electronics devices.

While reviews are often good enough for cameras and computers, "fashion shopping is about discovering something that fits your taste and feels right," said Google Product Management Director Munjal Shah, who brought his assets to Google to create lets users not only create their own curated boutique but also access boutiques curated by the people who popularize fashion items, including celebrities, designers and stylists. Such people help decide what's hot or not. Users click links to navigate to e-commerce Websites to make their purchases.

Here's how it works. As with before Google acquired it in August, uses computer vision and machine learning software to visually analyze users' preferences and suggest items they might like.

Google paired this technology with the taste-maker boutiques, culled from visual quizzes to teach the visual search engine to grok their style and to tell users what colors, patterns and brands worked and which ones didn't.

This, along with filters by genre, silhouette, pattern, color families and sizes, helps users narrow the myriad permutations of clothing combinations from which to choose.

"Our machine learning algorithms use this information to enable you to shop all of the inventory in the style of that taste-maker, on top of the 50 items they've hand curated," Shah said in his blog post. also lets users build their own personalized boutique and receive product recommendations that match their tastes.

For example, a user can search for shoes and see suggestions for matching outfits to the right of their search results. There are also style rules to let users know what goes well with what and what doesn't.

Google, which created a application for Apple's iPad, is making available only for U.S. women for this holiday shopping season. Expect an expansion to men's fashion and other countries next year. is the second sign that Google is thinking hard about e-commerce for the 2010 holiday season.

The company upgraded its homegrown Product Search engine Nov. 15, partnering with more than 70 retailers and software makers such as Oracle, JDA and Epicor to index inventories of local retail stores.