MAB seems to find a local maxima subject to input biases whereas an AB test is a... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		cfarm on May 27, 2019 \| parent \| context \| favorite \| on: The multi-armed bandit problem (2012) MAB seems to find a local maxima subject to input biases whereas an AB test is aimed to figure out a scientific truth and isolates out all potential biases in the system. I'd be curious to hear where a MAB approach and an AB test did not yield the same results and why that happened.

orasis on May 28, 2019 [–]

AB testing doesn’t eliminate time based biases such as novelty of new features, special events, pay day, tax day, etc.

cfarm on May 28, 2019 | [–]

Sure - my point is that you could design the experiment such that it could. It's much more scientific.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact