What is collaborative filtering? Good question. If user A and user B both like something, the search engine can predict user A's future "likes" based on what user B "likes." This method shows relevant results for certain searches like movies, restaurants and stores because the search objects don't change that frequently and enough data can be gathered on them to show relevant results.

Bing's Ralf Herbrich, explains Matchbox in more detail on the Bing blog including:

Let's say over the past several weeks you have been reading and rating articles on electric cars. Traditional collaborative filtering techniques would look at other people who have read similar articles and cluster you with them. So when a new article comes out about Tesla's new model, as long as someone 'like you' interacts with it, it might get recommended to you. But how does that first 'someone like you' find it in the first place? That's where Matchbox can help.

Rather than simply relying on the actions of others, the Matchbox technology uses the wealth of information about the entities mentioned in an article. In this case, Matchbox knows that Tesla is an 'electric car'. With this additional information, it can display "Tesla Model S: 300 miles on 1 charge" to you without having to receive input from other like-minded individuals.

Herbrich also stated that the technology is being developed quickly so that this personalized search experience can be available across Bing Mobile, Bing News, Bing Web and AdCenter.

As the first major Matchbox project, Bing is releasing Project Emporia; a web and mobile phone app, that uses multiple filters for personalization, including Matchbox, social recommendations (primarily via Twitter), and collaborative filtering.

It's not yet known when Matchbox will be integrated into Bing search results, but once we find out, we will let you know.