This topic provides an introduction to feature selection algorithms and describes the feature selection functions available in Statistics and Machine Learning Toolbox™.
Feature selection reduces the dimensionality of data by selecting only a subset of measured features (predictor variables) to create a model. Feature selection algorithms search for a subset of predictors that optimally models measured responses, subject to constraints such as required or excluded features and the size of the subset. The main benefits of feature selection are to improve prediction performance, provide faster and more costeffective predictors, and provide a better understanding of the data generation process [1]. Using too many features can degrade prediction performance even when all features are relevant and contain information about the response variable.
You can categorize feature selection algorithms into three types:
Filter Type Feature Selection — The filter type feature selection algorithm measures feature importance based on the characteristics of the features, such as feature variance and feature relevance to the response. You select important features as part of a data preprocessing step and then train a model using the selected features. Therefore, filter type feature selection is uncorrelated to the training algorithm.
Wrapper Type Feature Selection — The wrapper type feature selection algorithm starts training using a subset of features and then adds or removes a feature using a selection criterion. The selection criterion directly measures the change in model performance that results from adding or removing a feature. The algorithm repeats training and improving a model until an algorithm its stopping criteria are satisfied.
Embedded Type Feature Selection — The embedded type feature selection algorithm learns feature importance as part of the model learning process. Once you train a model, you obtain the importance of the features in the trained model. This type of algorithm selects features that work well with a particular learning process.
In addition, you can categorize feature selection algorithms according to whether or not an algorithm ranks features sequentially. The minimum redundancy maximum relevance (MRMR) algorithm and stepwise regression are two examples of the sequential feature selection algorithm. For details, see Sequential Feature Selection.
For regression problems, you can compare the importance of predictor variables
visually by creating partial dependence plots (PDP) and individual conditional
expectation (ICE) plots. For details, see plotPartialDependence
.
For classification problems, after selecting features, you can train two models
(for example, a full model and a model trained with a subset of predictors) and
compare the accuracies of the models by using the compareHoldout
, testcholdout
, or testckfold
functions.
Feature selection is preferable to feature transformation when the original features and their units are important and the modeling goal is to identify an influential subset. When categorical features are present, and numerical transformations are inappropriate, feature selection becomes the primary means of dimension reduction.
Statistics and Machine Learning Toolbox offers several functions for feature selection. Choose the appropriate feature selection function based on your problem and the data types of the features.
Function  Supported Problem  Supported Data Type  Description 

fscmrmr  Classification  Categorical and continuous features  Rank features sequentially using the Minimum Redundancy Maximum Relevance (MRMR) Algorithm. For examples, see the function reference
page 
fscnca *  Classification  Continuous features  Determine the feature weights by using a diagonal adaptation of neighborhood component analysis (NCA). This algorithm works best for estimating feature importance for distancebased supervised models that use pairwise distances between observations to predict the response. For details, see the function
reference page

fsrnca *  Regression  Continuous features  Determine the feature weights by using a diagonal adaptation of neighborhood component analysis (NCA). This algorithm works best for estimating feature importance for distancebased supervised models that use pairwise distances between observations to predict the response. For details, see the function
reference page

fsulaplacian  Unsupervised learning  Continuous features  Rank features using the Laplacian Score. For examples, see the function reference
page 
relieff  Classification and regression  Either all categorical or all continuous features  Rank features using the ReliefF algorithm for classification and the RReliefF algorithm for regression. This algorithm works best for estimating feature importance for distancebased supervised models that use pairwise distances between observations to predict the response. For examples, see the
function reference page 
sequentialfs  Classification and regression  Either all categorical or all continuous features  Select features sequentially using a custom criterion.
Define a function that measures the characteristics of data
to select features, and pass the function handle to the

*You can also consider fscnca
and
fsrnca
as embedded type feature selection functions
because they return a trained model object and you can use the object functions
predict
and loss
. However, you
typically use these object functions to tune the regularization parameter of the
algorithm. After selecting features using the fscnca
or
fsrnca
function as part of a data preprocessing step,
you can apply another classification or regression algorithm for your
problem.
Function  Supported Problem  Supported Data Type  Description 

sequentialfs  Classification and regression  Either all categorical or all continuous features  Select features sequentially using a custom criterion.
Define a function that implements a supervised learning
algorithm or a function that measures performance of a
learning algorithm, and pass the function handle to the
For examples, see the function
reference page 
Function  Supported Problem  Supported Data Type  Description 

DeltaPredictor property of a ClassificationDiscriminant model object  Linear discriminant analysis classification  Continuous features  Create a linear discriminant analysis classifier by
using For examples, see these topics:

fitcecoc with
templateLinear  Linear classification for multiclass learning with highdimensional data  Continuous features  Train a linear classification model by using
For an example, see Find Good Lasso Penalty Using CrossValidation. This example
determines a good lassopenalty strength by evaluating
models with different strength values using 
fitclinear  Linear classification for binary learning with highdimensional data  Continuous features  Train a linear classification model by using
For an example, see Find Good Lasso Penalty Using CrossValidated AUC. This example
determines a good lassopenalty strength by evaluating
models with different strength values using the AUC values.
Compute the crossvalidated posterior class probabilities by
using 
fitrgp  Regression  Categorical and continuous features  Train a Gaussian process regression (GPR) model by
using For examples, see these topics:

fitrlinear  Linear regression with highdimensional data  Continuous features  Train a linear regression model by using
For examples, see these topics:

lasso  Linear regression  Continuous features  Train a linear regression model with Lasso regularization by using For examples, see the function
reference page

lassoglm  Generalized linear regression  Continuous features  Train a generalized linear regression model with Lasso regularization by using
For details, see the function
reference page

oobPermutedPredictorImportance ** of ClassificationBaggedEnsemble  Classification with an ensemble of bagged decision trees (for example, random forest)  Categorical and continuous features  Train a bagged classification ensemble with tree
learners by using For examples, see the
function reference page and the topic 
oobPermutedPredictorImportance ** of RegressionBaggedEnsemble  Regression with an ensemble of bagged decision trees (for example, random forest)  Categorical and continuous features  Train a bagged regression ensemble with tree learners
by using For examples, see the
function reference page 
predictorImportance ** of ClassificationEnsemble  Classification with an ensemble of decision trees  Categorical and continuous features  Train a classification ensemble with tree learners by
using For examples, see the function reference
page 
predictorImportance ** of ClassificationTree  Classification with a decision tree  Categorical and continuous features  Train a classification tree by using For examples, see the function reference
page 
predictorImportance ** of RegressionEnsemble  Regression with an ensemble of decision trees  Categorical and continuous features  Train a regression ensemble with tree learners by using
For examples, see the function reference
page 
predictorImportance ** of RegressionTree  Regression with a decision tree  Categorical and continuous features  Train a regression tree by using For examples, see the function
reference page 
stepwiseglm  Generalized linear regression  Categorical and continuous features  Fit a generalized linear regression model using
stepwise regression by using
For
details, see the function reference page

stepwiselm  Linear regression  Categorical and continuous features  Fit a linear regression model using stepwise regression
by using For details, see the function
reference page

**For a treebased algorithm, specify 'PredictorSelection'
as 'interactioncurvature'
to use the interaction test for
selecting the best split predictor. The interaction test is useful in
identifying important variables in the presence of many irrelevant variables.
Also, if the training data includes many predictors, then specify
'NumVariablesToSample'
as 'all'
for
training. Otherwise, the software might not select some predictors,
underestimating their importance. For details, see fitctree
, fitrtree
, and templateTree
.
[1] Guyon, Isabelle, and A. Elisseeff. "An introduction to variable and feature selection." Journal of Machine Learning Research. Vol. 3, 2003, pp. 1157–1182.