maciejkula / spotlight

Deep recommender models using PyTorch.
MIT License
3k stars 428 forks source link

Hyperparameters settings for Implicit matrix factorization algorithm. #152

Open RuihongQiu opened 5 years ago

RuihongQiu commented 5 years ago

New beginner for recommender system. I don't know how to tune the hyperparameters and don't know what is a literally good result. I would like to know what is a proper setting of hyperparameters for the simple Implicit matrix factorization method.

My example codes is like this. image

The result is like this. image

The MRR and the RMSE scores seem to be not that good for training set or testing, though there is clear overfitting here.

Thanks!

maciejkula commented 5 years ago

I would encourage you not to use the explicit models. Try the implicit model and see if you can improve MRR?

RuihongQiu commented 5 years ago

I will have a try. Thanks!