ALS BiasedMF

This page analyzes the hyperparameter tuning results for biased matrix factorization with ALS.

Parameter Search Space

Parameter	Type	Distribution	Values	Selected
embedding_size	Integer	LogUniform	4 ≤ \(x\) ≤ 512	313
regularization.user	Float	LogUniform	1e-05 ≤ \(x\) ≤ 1	0.158
regularization.item	Float	LogUniform	1e-05 ≤ \(x\) ≤ 1	0.0151
damping.user	Float	LogUniform	1e-12 ≤ \(x\) ≤ 100	3.06e-10
damping.item	Float	LogUniform	1e-12 ≤ \(x\) ≤ 100	1.46

Final Result

Searching selected the following configuration:

{
    'embedding_size': 313,
    'regularization': {'user': 0.15778630974585842, 'item': 0.015106952175028448},
    'damping': {'user': 3.063168859977759e-10, 'item': 1.4636360311142516},
    'epochs': 6
}

With these metrics:

{
    'RBP': 0.08185716969258171,
    'LogRBP': 1.291460586281584,
    'NDCG': 0.3906712754513665,
    'RecipRank': 0.1941867238884197,
    'RMSE': 0.7520846411664338,
    'TrainTask': '4510a89c-61e3-44c3-b442-791f5699922c',
    'TrainTime': None,
    'TrainCPU': None,
    'max_epochs': 30,
    'done': True,
    'training_iteration': 6,
    'trial_id': '3d07f9d4',
    'date': '2025-05-05_10-29-42',
    'timestamp': 1746455382,
    'time_this_iter_s': 21.478567123413086,
    'time_total_s': 142.84648752212524,
    'pid': 4077948,
    'hostname': 'CCI-ws21',
    'node_ip': '10.248.127.152',
    'config': {
        'embedding_size': 313,
        'regularization': {'user': 0.15778630974585842, 'item': 0.015106952175028448},
        'damping': {'user': 3.063168859977759e-10, 'item': 1.4636360311142516},
        'epochs': 6
    },
    'time_since_restore': 142.84648752212524,
    'iterations_since_restore': 6
}

Parameter Analysis

Embedding Size

The embedding size is the hyperparameter that most affects the model’s fundamental logic, so let’s look at performance as a fufnction of it:

Learning Parameters

Iteration Completion

How many iterations, on average, did we complete?

How did the metric progress in the best result?

How did the metric progress in the longest results?