HACKER Q&A
📣 thisismyswamp

Should HN use a different time algorithm for post ranking?


I came across this old post by @gojomo: https://news.ycombinator.com/item?id=4758798

which suggests a different concept of time for ranking posts

the main issue trying to be solved is that currently there is an incentive to find the best time to post something, as the variance in activity causes some times to make for a higher likelihood of post popularity

the suggestion is thus for there to be a different kind of time "tick" - instead of time itself, maybe a site-wide counter of activity such as number of views, votes, or submissions

I find the idea of removing the incentive to find the best time to post interesting. I think an ideal ranking algorithm drives the correlation between the time of posting to the number of impressions on a post to zero.

Interested in hearing y'alls thoughts!


  👤 thisismyswamp Accepted Answer ✓
this is another interesting comment on the issue: https://news.ycombinator.com/item?id=41977430

but crucially, it assumes that variations in submissions and voting activity are strongly correlated, which I imagine is not necessarily the case


👤 pvg
I find the idea of removing the incentive to find the best time to post interesting.

That's, more or less, what the second chance pool attempts to do. As do subcategories like https://news.ycombinator.com/show which effectively extend the 'visible time in queue' for Show HN posts.

I think the underexamined assumption in a lot of these analyses is that it's hard to get a post on the HN front page. But in reality, it's relatively straightforward with a whole pile of backup mechanisms. The mystique of 'magical posting hour' draws people in but it's a lot simpler to just produce a post that matches HN's (fairly broad and loose) interestingness criteria.