Interpretability
Train interpretable regression models and interpret complex regression
models
Use inherently interpretable regression models, such as linear models, decision trees, and generalized additive models, or use interpretability features to interpret complex regression models that are not inherently interpretable.
To learn how to interpret regression models, see Interpret Machine Learning Models.
Functions
Objects
LinearModel | Linear regression model |
RegressionGAM | Generalized additive model (GAM) for regression (Since R2021a) |
RegressionLinear | Linear regression model for high-dimensional data |
RegressionTree | Regression tree |
Topics
Model Interpretation
- Interpret Machine Learning Models
Explain model predictions using thelime
andshapley
objects and theplotPartialDependence
function. - Shapley Values for Machine Learning Model
Compute Shapley values for a machine learning model using interventional algorithm or conditional algorithm. - Introduction to Feature Selection
Learn about feature selection algorithms and explore the functions available for feature selection. - Explain Model Predictions for Regression Models Trained in Regression Learner App
To understand how trained regression models use predictors to make predictions, use global and local interpretability tools, such as partial dependence plots, LIME values, and Shapley values. - Use Partial Dependence Plots to Interpret Regression Models Trained in Regression Learner App
Determine how features are used in trained regression models by creating partial dependence plots.
Interpretable Models
- Train Linear Regression Model
Train a linear regression model usingfitlm
to analyze in-memory data and out-of-memory data. - Train Generalized Additive Model for Regression
Train a generalized additive model (GAM) with optimal parameters, assess predictive performance, and interpret the trained model. - Train Regression Trees Using Regression Learner App
Create and compare regression trees, and export trained models to make predictions for new data.