Decision Tree Regression (DTR)

Decision Tree Regression (DTR) is a Machine Learning algorithm used for Regression Tasks predicting continuous numeric values.

DTR algorithm creates a tree-like model where each node represents a feature, and branches represent the feature's value, ultimately leading to a predicted target value at the leaf nodes. By recursively partitioning the input space, DTR effectively builds a predictive model that can capture non-linear relationships within the data.


  • Unlike Decision Trees Tree classifiers that are used for Classification problems, DTR is designed to predict continuous numeric values rather than discrete class labels as output.
  • DTR selects the best Feature and value for splitting the data at each node to minimize the Variance within each subset.
  • The algorithm is prone to Overfitting, so techniques like tree pruning and limiting the maximum depth of the tree are often employed.
  • DTR is interpretable and can handle both numerical and Categorical Variables, but its interpretability comes at the cost of potential complexity in creating a model that generalizes well to new data.
  • DTR is useful Predictive Analysis, especially in scenarios requiring transparent models that allow human insight into the decision-making process.