Are your evaluation metrics top-heavy?

Screenshot from Netflix

The offline evaluation of recommendation systems is one of the most critical criteria for comparing different algorithms and selecting the best performing model to deploy in production. In this blog, we will take a look at some of the common metrics used to evaluate recommendation systems. Most of these metrics are defined in On Sampled Metrics for Item Recommendation paper where the authors discuss the properties of these metrics when evaluation data is sampled. …

Sangram Kapre

Machine Learning Engineer @ PlayStation

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store