Recommender Systems

Why Google wants to get closer to you (and why it bothers me more than Yahoo or Amazon’s personalization efforts)

/ rashmi / 4 Comments

Notice how much personalization Google has been putting out recently:
Personalized Search, the new release of the Toolbar has personalization, Google News now has recommended stories

Its clear why Google is doing this. Personalization is the next stage in the evolution of many products. It helps develop a closer relationship with users and get to know more about them. And most importantly, it provides a clear reason for Google to collect data and link it one individual. People do not want their web searches to be logged – partly because it does not provide any value for them. But we are fine with Amazon knowing a lot about us because there is a direct benefit in Amazon having our history. Google now wants the same type of relationship with you – its dear user. There are many business reasons for Google to pursue personalization.

Continue reading →

When recommendations go bad: Walmart & the “Planet of the Apes” fiasco

/ rashmi / 4 Comments

The recent recommendations fiasco at Walmart (people looking for Planet of the Apes were directed to movies about Martin Luther King Jr.). Expectedly this was found offensive many and was all over the blogosphere. Walmart now says it was due to some mis-cataloging by an employer in 2005. The end result: its not just that recommendation being changed, the whole recommender system is being taken down.

This is not the first time that recommender systems have been in the news for strange recommendations – though in the past its been about about ludicrous rather than offensive recommendations. For example, recall the “My TIVO thinks I am gay” article and Amazon recommending “underwear” to people looking for .NET books.

Continue reading →

Collaborative Filtering strikes back (this time with tags)

/ rashmi / 6 Comments

A long time ago, in a galaxy far away, I became interested in collaborative filtering. Well, it was five years ago, and I was at UC Berkeley, but it seems like eons ago.

What is collaborative filtering? Technically, it’s an algorithm for matching people with similar interests for the purpose of making recommendations. In non-technical terms, it’s a system for helping people find relevant content. Unlike search, where you parse a query to and the most relevant content, with collaborative filtering you find some way of gauging an individual’s interest in content, and then recommend what other similar users liked.

Continue reading →