Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Have pp based recomendation? #177

Closed
ArchyInUse opened this issue Oct 10, 2019 · 7 comments
Closed

Have pp based recomendation? #177

ArchyInUse opened this issue Oct 10, 2019 · 7 comments

Comments

@ArchyInUse
Copy link

ArchyInUse commented Oct 10, 2019

this is just a suggestion, have command argument for !r {pp} where the bot can recommend a random map from n-10 to n+10 pp (where n is the argument given)

for example: !r 300

@Tillerino
Copy link
Owner

Hi Archy. So I guess my question here is: what do you want to achieve?

@ArchyInUse
Copy link
Author

can you clarify the question? I was just recommending a feature, if it wasn't clear what I meant by a "random map from n-10 to n+10 pp" is if I type !r 300 the bot will return to me a map that if fc'd at a decent accuracy (98%-100%) will give me around 300pp.
Does this make sense?

@Tillerino
Copy link
Owner

I mean what's the story? Why would you want recommendations around a specific pp level?

@ArchyInUse
Copy link
Author

Ahh, well I'm a returning player and I've decayed overtime, it doesn't help that before that I stopped playing online so my skill level doesn't match quite well with my rank, almost half a year of improvement not going into ranked so yeah that's the story

@Tillerino
Copy link
Owner

We have something along those lines on the radar, see #11 :P

This issue will be referenced there if we need some more inspiration. Other than that I'll close this as a duplicate then :)

@ArchyInUse
Copy link
Author

in that case could you elaborate a little bit about how the recomendation system works? I'd like to try programming something like this for myself and it would be of great help

@Tillerino
Copy link
Owner

It's a statistical model of the kind if-you-liked-this-you-will-also-like-that. So similar to what amazon.com or Netflix do for their recommendations. There is no feature extraction or any other sort of dimensionality reduction going on, so I guess it's quite unique in that regard.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants