Arthur Lee
1 min readJul 10, 2020

--

Hi, it is an amazing blog.

In this sentence:

`we can ship new models without tuning the ranking function that combines expected revenue, engagement, and relevance.`

It looks like `relevance` is different from `engagement` and you use different methods to measure them?

I am curious how do you measure engagement?

In my opinion, even they are different, but I guess high relevance leads high engagement.

Just curious, thank you :)

--

--

Arthur Lee
Arthur Lee

Written by Arthur Lee

An machine learning engineer in Bay Area in the United States

No responses yet