IKNN Implicit

This page analyzes the hyperparameter tuning results for the ItemKNN scorer in implicit-feedback mode.

Parameter Search Space

Parameter Type Distribution Values Selected
max_nbrs Integer Uniform 2 ≤ \(x\) ≤ 50 49
min_nbrs Integer Uniform 1 ≤ \(x\) ≤ 5 1
min_sim Float LogUniform 1e-06 ≤ \(x\) ≤ 0.1 0.0123

Final Result

Searching selected the following configuration:

{'max_nbrs': 49, 'min_nbrs': 1, 'min_sim': 0.012257043366936223}

With these metrics:

{
    'RBP': 0.19593625620606014,
    'NDCG': 0.35120063383793404,
    'RecipRank': 0.35109683031890954,
    'TrainTask': 'c59ed465-ae2f-4298-bb3d-98c7bcd1936f',
    'TrainTime': 1.2043905329992413,
    'TrainCPU': 1.201783,
    'TestTask': '24cf5e8b-df3a-4f06-8f2d-85988a7bcd06',
    'TestTime': 401.7900918670057,
    'TestCPU': 403.26615799999996,
    'timestamp': 1745424983,
    'checkpoint_dir_name': None,
    'done': True,
    'training_iteration': 1,
    'trial_id': 'ec2f3_00021',
    'date': '2025-04-23_12-16-23',
    'time_this_iter_s': 409.9950828552246,
    'time_total_s': 409.9950828552246,
    'pid': 124507,
    'hostname': 'CCI-ws21',
    'node_ip': '10.248.127.152',
    'config': {'max_nbrs': 49, 'min_nbrs': 1, 'min_sim': 0.012257043366936223},
    'time_since_restore': 409.9950828552246,
    'iterations_since_restore': 1,
    'experiment_tag': '21_max_nbrs=49,min_nbrs=1,min_sim=0.0123'
}

Parameter Behavior

Neighborhood Size

The neighborhood size is key argument to consider, let’s look at RMSE with repspect to that:

Filtering

There are two filtering parameters we also test — minimum neighbors and mininmum simialrity.