Interpretability

Train interpretable classification models and interpret complex classification models

Use inherently interpretable classification models, such as linear models, decision trees, and generalized additive models, or use interpretability features to interpret complex classification models that are not inherently interpretable. To learn how to interpret classification models, see Interpret Machine Learning Models.

Gain insight into binary classifier decisions by generating counterfactual examples using the counterfactuals function. Counterfactual examples identify the minimal modifications needed to change the predicted label of a given observation.

Functions

expand all

Interpret Trained Model

Local Interpretable Model-Agnostic Explanations (LIME)

`lime`	Local interpretable model-agnostic explanations (LIME)
`fit`	Fit simple model of local interpretable model-agnostic explanations (LIME)
`plot`	Plot results of local interpretable model-agnostic explanations (LIME)

Shapley Values

`shapley`	Shapley values
`fit`	Compute Shapley values for query points
`plot`	Plot Shapley values using bar graphs
`boxchart`	Visualize Shapley values using box charts (box plots) (Since R2024a)
`plotDependence`	Plot dependence of Shapley values on predictor values (Since R2024b)
`swarmchart`	Visualize Shapley values using swarm scatter charts (Since R2024a)

Partial Dependence

`partialDependence`	Compute partial dependence
`plotPartialDependence`	Create partial dependence plot (PDP) and individual conditional expectation (ICE) plots

Train Interpretable Model

`fitcgam`	Fit generalized additive model (GAM) for binary classification
`fitclinear`	Fit binary linear classifier to high-dimensional data
`fitctree`	Fit binary decision tree for multiclass classification

Generate Counterfactuals

counterfactuals Generate counterfactual examples for observation (Since R2026a)

Objects

`ClassificationGAM`	Generalized additive model (GAM) for binary classification
`ClassificationLinear`	Linear model for binary classification of high-dimensional data
`ClassificationTree`	Binary decision tree for multiclass classification

Topics

Model Interpretation

Interpret Machine Learning Models
Explain model predictions using the lime and shapley objects and the plotPartialDependence function.
Shapley Values for Machine Learning Model
Compute Shapley values for a machine learning model using interventional algorithm or conditional algorithm.
Shapley Output Functions
Stop Shapley computations, create plots, save information to your workspace, or perform calculations while using shapley.
Introduction to Feature Selection
Learn about feature selection algorithms and explore the functions available for feature selection.
Explain Model Predictions for Classifiers Trained in Classification Learner App
To understand how trained classifiers use predictors to make predictions, use global and local interpretability tools, such as permutation importance plots, partial dependence plots, LIME values, and Shapley values.
Use Partial Dependence Plots to Interpret Classifiers Trained in Classification Learner App
Determine how features are used in trained classifiers by creating partial dependence plots.

Interpretable Models

Train Generalized Additive Model for Binary Classification
Train a generalized additive model (GAM) with optimal parameters, assess predictive performance, and interpret the trained model.
Train Decision Trees Using Classification Learner App
Create and compare classification trees, and export trained models to make predictions for new data.
Classification Using Nearest Neighbors
Categorize data points based on their distance to points in a training data set, using a variety of distance metrics.