News for hackers. Stuff that matters.
Re:Interpreting A/B test results: false positives and statis... by dmitriid on Friday October 29, 2021 @04:01PM (#29042925)
Before interpreting A/B results, the main question that needs to be asked: "what is it that you're A/B testing?"

For too many companies, it's testing "engagement" which leads to hiding functionality (more clicks is more engagement), reducing info density (more time spent is more engagement) etc.

And coming from Netflix... I don't think there's a single person who likes that when you browse Netflix it autoplays random videos (not even trailers) with audio at full volume. But yeah, A/B tests something something. So I wish Netflix learned from their own teachings.

Re:Interpreting A/B test results: false positives and statis... by mobjack on Friday October 29, 2021 @05:30PM (#29043768)
I've A/B tested hiding functionality and reducing info density increased the number of people spending money on the site.

I was completely shocked by seeing those results initially and dove deep to look for any other negative effects from these changes but could not find any. I've repeated similar tests and the results are often similar.

From that experience, I've learned that most people are not like me or the HN crowd. The things that you complain about could actually make things easier for the majority.

Re:Interpreting A/B test results: false positives and statis... by rancar2 on Saturday October 30, 2021 @12:49AM (#29046064)
I’ve A/B tested this at scale with millions of users across different verticals globally. In many situations, focusing on core functions and clear information presentation helps guide the user to using the site as primarily intended based on their primary intent. It’s tough for most product teams to realize that most users really don’t want all that additional functionality they built.
Re:Interpreting A/B test results: false positives and statis... by dmitriid on Saturday October 30, 2021 @02:34AM (#29046544)
Yes, you're training users to deal with unnecessary complexity, and then the competitors with less complexity swoop in and take your user base.

Thankfully for businesses with built-in complexity and unfortunately for everyone, other businesses also have the same mindset.

Re:Interpreting A/B test results: false positives and statis... by dafelst on Friday October 29, 2021 @04:29PM (#29043215)
People may not like that feature (I sure don't), but I would bet a decent sum that feature didn't drive increases in negative metrics like churn, and increased positive metrics like hours watched, perhaps by causing people to scroll through more of the library faster, or perhaps drawing people in with the previews. Or maybe they just saw in improvement in a non-core metric like "distance scrolled" with no other negative effects and said, "meh, ship it". Both seem likely.

Of course this is the danger of any sort of behavioral metric driven optimization strategy - you may trade negative customer sentiment for positive business outcomes. That's where the real decision making comes about, i.e. are you willing to make that trade? It seems that in this case, Netflix was.

Re:Interpreting A/B test results: false positives and statis... by type_enthusiast on Friday October 29, 2021 @04:21PM (#29043128)
(disclaimer: I work for Netflix. Edit: I should clarify that I wasn't involved with this article in any way)

You can disable the behavior you mentioned. Go to your profile settings, and under "Playback Settings" you can uncheck "Autoplay previews while browsing on all devices".

Re:Interpreting A/B test results: false positives and statis... by dmitriid on Saturday October 30, 2021 @02:31AM (#29046530)
> You can disable the behavior you mentioned.

I know I can. But then I can't play trailers for movies/shows where I want to see the trailer.