[The Netflix Tech Blog] BigDataFr recommends: Innovating Faster on Personalization Algorithms at Netflix Using Interleaving

algorithms

BigDataFr recommends: Innovating Faster on Personalization Algorithms at Netflix Using Interleaving

[…] The Netflix experience is powered by a family of ranking algorithms, each optimized for a different purpose. For instance, the Top Picks row on the homepage makes recommendations based on a personalized ranking of videos, and the Trending Now row also incorporates recent popularity trends. These algorithms, along with many others, are used together to construct personalized homepages for over 100 million members.
At Netflix, we strive to continually improve our recommendations. The development process begins with the creation of new ranking algorithms and the evaluation of their performance offline. We then leverage A/B testing to conduct online measurements of core evaluation metrics that align closely with our business objective of maximizing member satisfaction.[…]

Read more
By Juliette Aurisset, Michael Ramm, Joshua Parks
Source: medium.com

Laisser un commentaire

Votre adresse de messagerie ne sera pas publiée. Les champs obligatoires sont indiqués avec *