# Explain a model Model / explain variable importance, partial dependence, SHAP, model inspection Page: ## Status Not built yet. arcform does not do this yet. [Its place on the roadmap](https://meridian.online/roadmap#explain-a-model) ## Variants - Rank inputs by importance: Measure how much each input column contributes to a trained model across a dataset. - [Show how one input moves the prediction](https://meridian.online/operations/explain-a-model/show-how-one-input-moves-the-prediction): Compute the average prediction across a grid of values of one input, holding the data otherwise as it is. - [Explain each prediction](https://meridian.online/operations/explain-a-model/explain-each-prediction): Attribute each scored row's prediction to the input values that pushed it up or down, as with SHAP or local surrogates. - [Inspect a model's structure](https://meridian.online/operations/explain-a-model/inspect-a-models-structure): Read out a model's internals, such as its coefficients, trees, rules, centroids or formula. ## What other tools call it Meridian's classification; an independent blind rating agreed on 86.2% of 312 rows (exact class, version 2). - Alteryx Designer: [`Model Coefficients`](https://help.alteryx.com/current/en/designer/tools/predictive/model-coefficients-tool.html) (read 2026-09-27) - Alteryx Designer: [`Variance Inflation Factors`](https://help.alteryx.com/current/en/designer/tools/predictive/variance-inflation-factors-tool.html) (read 2026-09-27) - KNIME Analytics Platform: [`Decision Tree View`](https://api.hub.knime.com/nodes/*Vm4p8b0cVbyXueLa?details=full) (read 2026-09-27) - KNIME Analytics Platform: [`Decision Tree to Image`](https://api.hub.knime.com/nodes/*orOzsHYPnOJsY3H9?details=full) (read 2026-09-27) - KNIME Analytics Platform: [`KNIME Machine Learning Interpretability Extension (extension)`](https://api.hub.knime.com/extensions/org.knime.features.mli) (read 2026-09-27) - KNIME Analytics Platform: [`KNIME Rule Viewer (Legacy) (extension)`](https://api.hub.knime.com/extensions/org.knime.features.ext.md) (read 2026-09-27) - KNIME Analytics Platform: [`Tree Ensemble Model Extract`](https://api.hub.knime.com/nodes/*lKQv55nTvgGp2g12?details=full) (read 2026-09-27) - KNIME Analytics Platform: [`Tree Ensemble Statistics`](https://api.hub.knime.com/nodes/*54voSTRPIfQ-lMPR?details=full) (read 2026-09-27) - RapidMiner Studio: [`Cluster Model Visualizer`](https://docs.rapidminer.com/latest/studio/operators/modeling/segmentation/cluster_model_visualizer.html) (read 2026-09-27) - RapidMiner Studio: [`Create Formula`](https://docs.rapidminer.com/latest/studio/operators/modeling/predictive/create_formula.html) (read 2026-09-27) - RapidMiner Studio: [`Explain Predictions`](https://docs.rapidminer.com/latest/studio/operators/scoring/explain_predictions.html) (read 2026-09-27) - RapidMiner Studio: [`Extract Cluster Prototypes`](https://docs.rapidminer.com/latest/studio/operators/modeling/segmentation/extract_prototypes.html) (read 2026-09-27) - RapidMiner Studio: [`GLM Contribution`](https://docs.rapidminer.com/latest/studio/operators/extensions/Operator%20Toolbox/models/glm_contribution.html) (read 2026-09-27) - RapidMiner Studio: [`Generate Partial Dependency Plot Data`](https://docs.rapidminer.com/latest/studio/operators/extensions/Operator%20Toolbox/blending/generate_pdp.html) (read 2026-09-27) - RapidMiner Studio: [`Get Decision Tree Path`](https://docs.rapidminer.com/latest/studio/operators/extensions/Operator%20Toolbox/models/get_dectree_path.html) (read 2026-09-27) - RapidMiner Studio: [`Local Interpretation (LIME)`](https://docs.rapidminer.com/latest/studio/operators/extensions/Operator%20Toolbox/models/get_interpretation_subprocess.html) (read 2026-09-27) - RapidMiner Studio: [`Model Simulator`](https://docs.rapidminer.com/latest/studio/operators/scoring/model_simulator.html) (read 2026-09-27) - RapidMiner Studio: [`Visualize Model by SOM`](https://docs.rapidminer.com/latest/studio/operators/validation/visual/visualize_model_by_som.html) (read 2026-09-27) - RapidMiner Studio: [`Weight by Tree Importance`](https://docs.rapidminer.com/latest/studio/operators/modeling/feature_weights/weight_by_forest.html) (read 2026-09-27) - Yggdrasil Decision Forests: [`GBT model accessors (group)`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/gradient_boosted_trees_model/gradient_boosted_trees_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`analyze`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/generic_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`analyze_model_and_dataset`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/cli/analyze_model_and_dataset.cc) (read 2026-09-27) - Yggdrasil Decision Forests: [`analyze_prediction`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/generic_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`compute_variable_importances`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/cli/compute_variable_importances.cc) (read 2026-09-27) - Yggdrasil Decision Forests: [`describe`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/generic_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`get_tree / get_all_trees / iter_trees`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/decision_forest_model/decision_forest_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`in_bag_example_indices`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/learner/specialized_learners_pre_generated.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`num_examples_per_tree`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/isolation_forest_model/isolation_forest_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`num_trees / num_nodes`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/decision_forest_model/decision_forest_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`predict_shap`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/generic_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`print_tree`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/decision_forest_model/decision_forest_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`show_model`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/cli/show_model.cc) (read 2026-09-27) - Yggdrasil Decision Forests: [`variable_importances`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/generic_model.py) (read 2026-09-27) - Yggdrasil Decision Forests: [`winner_takes_all`](https://github.com/google/yggdrasil-decision-forests/blob/0a54b57c95ff0cf42ecf0310ace0513a4f32cb65/yggdrasil_decision_forests/port/python/ydf/model/random_forest_model/random_forest_model.py) (read 2026-09-27)