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

Prior Knowledge (http://www.priorknowledge.com) has a very similar API but a more interesting underlying model. They model the full joint distribution of the data, so any variables can be missing not just the outcome. They also are able to return the joint probability distribution over unknowns, which is extremely useful in terms of quantifying uncertainty.

The model itself appears very flexible:

http://blog.priorknowledge.com/blog/beyond-correlation/

I'm not affiliated with these guys but they are clearly doing the most interesting work in this area.



Are they a Y Combinator company, by any chance?

Curious as some of the language is very similar to a series of stealth job postings here over the past ~6 months.


Looks really interesting. Any chance you know where to get an invite code for the beta?


Just submit your email and we'll get you into the beta very quickly:

https://dev.priorknowledge.com/login?next=/


They are pretty responsive from my experience. The beta is definitely open.


True I had my invite in a couple of hours.


I'm very curious to see (a) what sort of generative model they're using under the hood, and (b) how they do inference efficiently enough to not dedicate a cluster to each customer.




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

Search: