Skip to main content
Configuration parameters for different model task types and evaluation metrics. ModelTaskParams defines task-specific parameters that control how models are evaluated and monitored within Fiddler. Different model types (classification, regression, ranking) require different parameters to properly compute metrics and perform analysis. These parameters are essential for accurate metric computation, proper baseline establishment, and meaningful performance monitoring across different model types and use cases.

​
Examples

Configuration for binary classification: 
binary_params = ModelTaskParams(
    binary_classification_threshold=0.5,
    target_class_order=["negative", "positive"]
)
Configuration for multi-class classification with class weights: 
multiclass_params = ModelTaskParams(
    target_class_order=["class_a", "class_b", "class_c"],
    class_weights=[0.3, 0.5, 0.2],
    weighted_ref_histograms=True
)
Configuration for ranking models: 
ranking_params = ModelTaskParams(
    group_by="query_id",
    top_k=10,
    target_class_order=["not_relevant", "relevant", "highly_relevant"]
)
Configuration for imbalanced datasets: 
imbalanced_params = ModelTaskParams(
    binary_classification_threshold=0.3,
    class_weights=[0.1, 0.9],
    weighted_ref_histograms=True
)

​
binary_classification_threshold

Threshold for labels

​
target_class_order

Order of target classes

​
group_by

Query/session id column for ranking models

​
model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

​
top_k

Top k results to consider when computing ranking metrics

​
class_weights

Weight of each classes

​
weighted_ref_histograms

Whether baseline histograms must be weighted or not while drift metrics