Posts from all blogs: A/B testing

Using Deep Learning at Scale in Twitter’s Timelines

(This post was co-authored by Anton Andryeyev from our timelines quality team)

For more than a year now since we enhanced our timeline to show the best Tweets for you first, we have worked to improve the underlying algorithms in order to surface content that is even more relevant to you.

Read more...

Power, minimal detectable effect, and bucket size estimation in A/B tests

Figuring out the minimal number of users one must expose to an experimental treatment to collect actionable data is not a trivial task. We explain how we approach this problem with Twitter’s A/B testing platform (DDG), and how we communicate issues of statistical power to experimenters.

Read more...