Recommendations
Measuring the Impact of Personalized Recommendations
Our short summary of Netflix’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on netflixtechblog.com (opens in a new tab)Problem
How much value does personalized recommendation add to user viewing?
Solution
They built a behavioral model that separates a member’s underlying preference from the extra effect of a recommendation, allowing causal measurement of recommendation impact.
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on netflixtechblog.com (opens in a new tab)