Someone posted a question on Quora asking how Netflix tags its movies as inputs for its categorization and recommendation engine. Neil Hunt, Chief Product Officer at Netflix, answered.
There’s another question of how the Netflix recommendation engine works.
After IBM’s Watson won its recent Jeopardy challenge, a lot of discussion has been about what the powerful computer system will be used for next. Check out an interview.
Hunch has put together a new demonstration of their service in the form of a game. They’ve taken lots of questions answered by their users and found correlations. The game tests your ability to pick the right answer. Give the correlation game a try. Here’s the Hunch blog post with more info.
Instead of each site you visit having its own recommendation algorithms, Inveni has come up with a different approach. They allow you to create an Inveni profile and then share it with sites and advertisers as you like. They are starting with movie and tv recommendations
Here is the Techcrunch article and a video.
Darren Vengroff, chief scientist at RIchRelevance, explains how he is working to make recommendation systems smarter. Check out the Fast Company article.
For some, the thought of building a statistical model gives them a headache, but for others combining the two is the answer. Check out My Migraine Journal where you can record your various daily activities and leverage the site’s model to help you figure out what might be causing your headaches. Here’s an article from Columbia -Statistical Modeling, Causal Interference, and Social Science Blog with more info.
The FIrst Coffee blog reports that SAS and Netezza have expanded their partnership to allow for SAS model code to run in parallel on Netezza’s TwinFin appliance.
Check out this Techcrunch article highlighting Myspace’s new recommendation system, Qizmt. It’s built on a mapreduce framework.
In an effort to increase user engagement, satisfaction, and profitability, many websites are offering their users various types of recommendations. Many people are familiar with Amazon.com’s people who bought also bought or people who browsed also browsed. But how do they do that?
Darren Vengroff, chief scientist from RichRelevance, explains some of the components of a recommendation system in a GigaOM article.
Netflix just implemented some updates to their star rating predictions based on some work done on the Netflix Prize. Here’s what Todd Yellin, Director of Product Management, and Jon Sanders, Director of Recommendation Systems have to say on the Netflix Blog.
