ReadWriteWeb

Between the iTunes Genius Sidebar, Amazon's recommender system and Pandora's virtual DJ, recommender systems are now getting close to knowing my tastes better than I do.

There's a certain seductive attraction to the idea that collaborative filtering and artificial intelligence could hand us our heart's desire before our hearts even think of it. Think of the time and effort I could save if I didn't have to make decisions about what to eat, buy, wear, listen to, watch or read. When it comes right down to it, free will is a genuine time suck, and seriously cuts into my blogging schedule.

Last week we looked at Baynote, a recommendations company that focuses on real-time community behavior instead of personalization. Today we look at a company that takes a broader approach: richrelevance uses personalization extensively, plus the wisdom of the crowds when relevant. richrelevance claims that its approach is "adaptive AI" and that customers such as Sears and KMart are using its technology. We spoke to richrelevance founder and CEO David Selinger (ex-Amazon), to find out more about the product and what makes it different to Baynote and others.

In a recent post, we looked at recommendation systems, briefly reviewing how Amazon and Google have implemented their own systems for recommending products and content to their users.

We had the opportunity to speak with Satnam Alag, author of the recently published Collective Intelligence in Action, about what makes for a good recommendation system, where the technology is heading, and why Netflix is finding it so hard to improve its own system.