Classification and regression trees

By Niko Speybroeck. 2012

17,480 citations recorded by the source corpus.

Subfields: Agronomy and Crop Science, Genetics, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Agronomy and Crop Science

In Genetics

In Statistical Learning Theory

Citations in the corpus

Analysis of a Random Forests Model (2010, methodology): “The tree is grown using CART methodology (Breiman et al., 1984) to maximum size, without pruning.”
Machine Learning Methods That Economists Should Know About (2019, methodology): “2 Regression Trees and Forests Regression trees (Breiman et al. [1984]), and their extension random forests (Breiman [2001a]) have become very popular and effective methods for flexibly estimating regression functions in settings where out-of-sample predictive power is important.”
Please Stop Explaining Black Box Models for High Stakes Decisions (2018, background): “…or uninterpretable because they do not choose a globally best choice (or approximately best choice) for the logical conditions [C4.5 and CART decision trees are an example, Quinlan, 1993, Breiman et al., 1984, as well as a vast number of models from the associative classiﬁcation literature].”
On the Art and Science of Machine Learning Explanations (2018, background): “X, g(X) A −→ htree (1) Decision trees can be represented as directed graphs where the relative positions of input features can provide insight into their importance and interactions [6].”
Learning Optimal Decision Trees with SAT (2018, background): “As a result, practical algorithms for learning decision trees are heuristic [Breiman et al., 1984; Quinlan, 1986], with no guarantees in terms of size compared to the optimal.”
Consistent Individualized Feature Attribution for Tree Ensembles (2018, methodology): “l feature importance values are calculated for an entire dataset (i.e., for all samples) in three primary ways: (1) Gain: A classic approach to feature importance introduced by Breiman et al. in 1984 [3] is based on gain. Gain is the total reduction of loss or impurity contributed by all splits for ”
A Survey of Methods for Explaining Black Box Models (2018, methodology): “in [87] present an approach for the probabilistic interpretation of the black box b Bayesian decision trees ensembles [10] through a quantitative evaluation of uncertainty of a Confident Decision Tree (CDT) cg.”
Interpretability via Model Extraction (2017, methodology): “We show that our active learning approach substantially improves over using CART [6], a standard decision tree learning algorithm.”
Interpreting Models via Single Tree Approximation (2016, background): “There are multiple choices of deﬁning the information gain in the literature [Breiman et al., 1984, Loh and Shih, 1997].”
Making Tree Ensembles Interpretable (2016, methodology): “One of the most widely used methods would be a decision tree such as CART (Breiman et al., 1984).”
Learning Certifiably Optimal Rule Lists (2017, methodology): “Figure 3 summarizes di erences in accuracy and model size for CORELS and other tree (CART, C4.5) and rule list (RIPPER, SBRL) learning algorithms.”
Interpretable classification models for recidivism prediction (2015, methodology): “• Classification and Regression Trees (CART): CART is a popular method to create decision trees through recursive partitioning of the input variables (Breiman et al. 1984), which is a predecessor to C5.”
Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor (2020, background): “, whether the mean squared error decrease is smaller than a set threshold Ts [51], and if so, this node is a leaf node).”