News for hackers. Stuff that matters.
Re:100ms in additional latency costs you 1% revenue? by tehlike on Sunday October 28, 2018 @12:31AM (#18319190)
I work in mobile ads, and for fun, i injected 50ms, 100ms, 250ms, 500ms latency in an experiment. The results were not as dramatic. 500ms had less than 1% impact. 50ms looked almost positive (didn't wait enough to have it statistically significant). This is 2018. Results are rather nonlinear, and different formats with different latency requirements had different results (like formats lending themselves to advance preloading would not be impacted at all even at 500ms, but ohers which had tighter UX requirements would).

I realize results are context-dependent, this is why everyone should make their own conclusions from their own analysis. You might have bigger bangs to make than shaving off some latency.

Re:100ms in additional latency costs you 1% revenue? by Kaveren on Sunday October 28, 2018 @06:37AM (#18320031)
> "50ms looked almost positive (didn't wait enough to have it statistically significant)"

Did you test the other delays (100ms, 250ms, and 500ms) for long enough to get statistical significance in this context?

Re:100ms in additional latency costs you 1% revenue? by JustSomeNobody on Sunday October 28, 2018 @09:07AM (#18320426)
> This is 2018.

Yeah, people are used to slow web sites.

Re:100ms in additional latency costs you 1% revenue? by slededit on Sunday October 28, 2018 @04:02PM (#18322792)
Ads aren't the first thing people look at though. If the rest of the page loads and content is visible then i won't leave because that ad I just had to see didn't become visible.
Re:100ms in additional latency costs you 1% revenue? by tehlike on Sunday October 28, 2018 @05:04PM (#18323184)
Exactly, but the point was all of this is context dependent.

For example, if you are involved in a 3rd party bidding where you bid on some other network's impression, you'll have a deadline to respond with a bid. Let's say that deadline is 500ms (it's not). 100ms increase in median would lose _significant_ amount of impressions in that case.