Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.


The Describe tabs provide model building information and feature details:

Leaderboard tab Description Source
Blueprint Provides a graphical representation of the data preprocessing and parameter settings via blueprint. Blueprints can be DataRobot- or user-generated. For DataRobot blueprints, the structure is decided once (after the partitioning stage), taking the dataset, project options, and column metadata into account. Values of auto hyperparameters may be decided later in the training process. Certain blueprint inputs and paths may be eliminated before training if the feature list does not have the corresponding feature types. For user-generated blueprints, the structure can be decided at any time.
Blueprint JSON Provides a model's Blueprint JSON representation, which can then be retrieved for programmatic usage and greater transparency. See above.
Coefficients Provides, for select models, a visual representation of the most important variables and a coefficient export capability. Training data
Constraints Forces certain XGBoost models to learn only monotonic (always increasing or always decreasing) relationships between specific features and the target. Training, Validation data
Data Quality Handling Report (Formerly Missing Values) Provides transformation and imputation information for blueprints. Training data
Eureqa Models Provides access to model blueprints for Eureqa generalized additive models (GAM), regression models, and classification models. The Pareto front uses the Eureqa validation set, a subset of DataRobot training. The plots shown for regression and classification models use validation data.
Log Lists operation status results. N/A
Model Info Displays model information. Training data
Rating Table Provides access to an export of the model’s complete, validated parameters. Training data

Updated August 23, 2023