Archive for November, 2006|Monthly archive page

Personal Recommender Systems Article

Fortune magazine has an interesting story about the rising importance of personalization and recommendation systems. I particularly like this excerpt:

“Building a personalized discovery mechanism will mean tapping into all the manners of expression, categorization, and opinions that exist on the Web today. It’s no easy feat, but if a company can pull it off and make the formula portable so it works on your mobile phone – well, such a tool could change not just marketing, but all of commerce.”

The article goes further by describing examples of recommendation systems such as those offered by Amazon, Netflix, and Pandora (my favourite).

It is not surprising not to find any examples of feed personalization or news recommendation systems in the article. Feeds 2.0 is still in private beta and obviously hasn’t gotten under the radar of the article’s author, and Findory (an interesting collaborative filtering news recommendation system) still hasn’t reached the audiences of Amazon, Netflix or Pandora. The article however mentions speculation about Google’s plans to get into the recommendation game.

It is true that automated personalization is an extremely hard problem to solve algorithmically, and it still seems like the “best” ones are only able to provide relevant information only a small fraction of the time. The quest for the perfect personalization and recommendation system is definitely not over and stll has a long way to go.

However, I like to keep an optimistic point of view on this issue: After all, I got this Fortune article on top of my reading list when I sorted posts “by Personalization” at Feeds 2.0 😉