Model description
This repo contains the model and the notebook on how to build and train a Keras model for Collaborative Filtering for Movie Recommendations.
Full credits to Siddhartha Banerjee.
Intended uses & limitations
Based on a user and movies they have rated highly in the past, this model outputs the predicted rating a user would give to a movie they haven't seen yet (between 0-1). This information can be used to find out the top recommended movies for this user.
Training and evaluation data
The dataset consists of user's ratings on specific movies. It also consists of the movie's specific genres.
Training procedure
The model was trained for 5 epochs with a batch size of 64.
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training Metrics
| Epochs | Train Loss | Validation Loss |
|---|---|---|
| 1 | 0.637 | 0.619 |
| 2 | 0.614 | 0.616 |
| 3 | 0.609 | 0.611 |
| 4 | 0.608 | 0.61 |
| 5 | 0.608 | 0.609 |
Model Plot
View Model Plot
- Downloads last month
- 32
Inference API (serverless) does not yet support tf-keras models for this pipeline type.