YouTube beefed up the machine learning engine behind the content recommendations in its iOS and Android applications.
Google vice president of YouTube product management Johanna Wright told CNET the improved recommendations engine is based on the same type of deep neural network technology Google uses to formulate its search results, adding:
Delivering a personal recommendation engine that shows YouTube really understand you is our goal. We’re able to do this because Google has some of the best machine learning in the world.
The home page of the iOS and Android apps was also redesigned to feature larger images, and Wright told CNET the new recommendation engine can turn up content that was uploaded less than one hour earlier, as well as new content from channels that users are subscribed to. She added:
We’ve made so many changes to machine learning system that we can more easily tell what videos people want to watch.
Wright told TechCrunch YouTube tested its new single ranked list with a small group of users over the past few weeks, and those users typically watched more videos for longer periods of time, adding:
We have made so many changes and we are getting so much better that we can now remove the grouping. Our experiments show that users really like this design. We are a very data-driven group, and all these changes run through A/B tests.
Readers: What are your initial thoughts on the update to YouTube’s iOS and Android apps?
Image courtesy of CNET.
from SocialTimes http://ift.tt/1Tv5Xjw
via IFTTT
No comments:
Post a Comment