Recommendation of problems based on the problems(/categories/tags) that user has not solved but yet popular!

[raj454raj]

[iamayushanand]

hi I have created a simple problem recommender using python. My cfhandle is FanOfTourist.It is a very basic python script. if you increase userdifficulty variable in the program it will recommend easier problems and if you decrease it it will recommend harder problems.

[raj454raj]

Our codebase(backend) is also in Python. It would be so easy for you to integrate it.

[afcruzs]

How much data does stopstalk have to train a recommender system?

I just found stop stalk and it seems extremely interesting!

[raj454raj]

Hey @afcruzs , current stats are something like this -

• 3600+ users and 400+ custom users
• ~3.7M submissions
• ~38k unique problems (with and without tags)

[afcruzs]

Awesome. What information is there for each problem and for each user?, in order to model the features. Hoy many tagged problems are there?

[raj454raj]

Hey @afcruzs : Can you please mail me at [email protected] , we can take the thread there :)