Data preprocessing and model training

Sparks's inbuilt function to train a model takes a dataframe of 'implicit preferences' given by users to some products. userID ~ user_id, productID ~ recording_id and preference ~ transformed count as represented by rows in playcounts dataframe.

Playcounts dataframe is loaded from HDFS in 0.00 mins and is of the form:

user_id recording_id playcount transformed_listencount

Here, playcount is the actual listen count whereas the transformed_listencount was calculated by applying the following function on playcounts.

No transformation applied to listen counts

Preprocessing of playcounts dataframe takes 0.00 mins. The preprocessed data divided the data into training and test data, in 5 : 1. The model was then trained on the training data using K-Folds Cross Validation with 5 folds. From the models trained, the one with least RMSE is selected to generate recommendations.

Of all the trained models, the model with the least RMSE value is chosen to generate recommendations. The model will be referred to as "best model".

Best model parameters are as follows:

Best model ID Best model rank Best model lmbda Best model iteration Best model alpha Best model RMSE
listenbrainz-recommendation-model-9c74f075-a9b8-406f-a1ff-60660481f105 100 0.1 10 3.0 10.765

Test RMSE for the best model is 20.153

Total time lapsed in data preprocessing and model training: 3.74 hours

Best Model saved in 0.10 mins

All the models trained in 3.73 hours

The following table gives information about all the models trained

model id rank lmbda iterations alpha RMSE
listenbrainz-recommendation-model-1435fabd-932b-4e28-8f83-759676570756 100 0.1 5 3.0 10.771
listenbrainz-recommendation-model-9c74f075-a9b8-406f-a1ff-60660481f105 100 0.1 10 3.0 10.765
listenbrainz-recommendation-model-29536e94-3fe7-4c81-98b4-1662a8fafb10 100 10.0 5 3.0 10.818
listenbrainz-recommendation-model-27f6f2dd-68a8-4f2e-b8b0-343a334b6195 100 10.0 10 3.0 10.817
listenbrainz-recommendation-model-688236a0-b564-443f-9ed8-14fe6cbe6173 120 0.1 5 3.0 10.771
listenbrainz-recommendation-model-8b0fc270-6f32-45ba-8278-6e141f771000 120 0.1 10 3.0 10.765
listenbrainz-recommendation-model-23ba64ba-52d0-40fd-8270-8e555d344ae5 120 10.0 5 3.0 10.818
listenbrainz-recommendation-model-26b477a0-ee71-4dde-a866-8abb54be92eb 120 10.0 10 3.0 10.817

Following are the parameters required to train the model

The Mean Squared Error (MSE) is a direct measure of the reconstruction error of the user-item rating matrix. It is defined as the sum of the squared errors divided by the number of observations. The squared error, in turn, is the square of the difference between the predicted rating for a given user-item pair and the actual rating.

Ratings are predicted for all the (user_id, recording_id) pairs in validation data, the predicted ratings are then subtracted with actual ratings and RMSE is calculated.

Note: Number of rows in a dataframe or number of elements in a dataframe (count information) is not included because it leads to unnecessary computation time.