DeepRecommender
DeepRecommender copied to clipboard
Add MovieLens example
Provide a recepie for training a model on MovieLens data (20M and 1M).
This should include the following:
- Data converter. Consider fixing/adjusting this script
- Train/Eval/Test split. Training test ratings should come before any Eval and Test ratings. See section 3.1 (Experiment setup) of this paper for details and Netflix converter for example.
-
An example train.sh, and test.sh for 20M and 1M MovieLens data sets which will train/eval and test the model correspondingly.
-
Choose model architecture and hyper parameters that give best eval RMSE you can get.