RandomForestClassifier<T>

Models & Types · AiDotNet.Classification.Ensemble

Random Forest classifier that combines multiple decision trees trained on random subsets.

Inheritance: ClassifierBase<T> → ProbabilisticClassifierBase<T> → EnsembleClassifierBase<T> → RandomForestClassifier<T>

Implements: ITreeBasedClassifier<T>

For Beginners

Random Forest is one of the most popular and powerful machine learning algorithms. It works by creating a “forest” of decision trees, where each tree:

  1. Is trained on a random subset of the data (bootstrap sampling)
  2. Considers only a random subset of features at each split
  3. Votes on the final prediction

This randomness makes the trees different from each other, and when combined, they create a robust classifier that:

  • Is resistant to overfitting
  • Handles both numerical and categorical features
  • Works well with default parameters
  • Provides feature importance scores

Example: Predicting customer churn

  • Tree 1 might focus on usage patterns and account age
  • Tree 2 might focus on customer service calls and billing
  • Tree 3 might focus on contract type and payment history
  • Together, they give a more reliable prediction than any single tree

How It Works

Random Forest is a meta estimator that fits a number of decision tree classifiers on various sub-samples of the dataset and uses averaging to improve predictive accuracy and control overfitting.

Example

// Create random forest classifier with bootstrap aggregation
var options = new RandomForestClassifierOptions<double>();
            
// Prepare training data
var features = new Matrix<double>(new double[,] { { 1.0, 1.1 }, { 1.2, 0.9 }, { 0.8, 1.0 }, { 5.0, 5.1 }, { 5.2, 4.9 }, { 4.8, 5.0 } });
var labels = new Vector<double>(new double[] { 0, 0, 0, 1, 1, 1 });
            
// Train multiple trees on random subsets of data and features
var result = new AiModelBuilder<double, Matrix<double>, Vector<double>>()
    .ConfigureModel(new RandomForestClassifier<double>(options))
    .Build(features, labels);
            
// Predict using majority vote across all trees in the forest
var newSample = new Matrix<double>(new double[,] { { 1.1, 1.0 } });
var prediction = result.Predict(newSample);
// Result is available in the returned value

Constructors

Constructor Summary
RandomForestClassifier(RandomForestClassifierOptions<T> options, IRegularization<T, Matrix<T>, Vector<T>> regularization) Initializes a new instance of the RandomForestClassifier class.

Properties

Property Summary
double OobScore_ { get; set; } Out-of-bag accuracy score (only available if OobScore is enabled).
int LeafCount { get; }
int MaxDepth { get; }
int NodeCount { get; }

Methods

Method Summary
Matrix<T> PredictProbabilities(Matrix<T> input) Averages the trees’ class probabilities.
ModelMetadata<T> GetModelMetadata()
void Train(Matrix<T> x, Vector<T> y) Returns the model type identifier for this classifier.