Learning Certifiably Optimal Rule Lists for Categorical Data

DOI10.48550/arXiv.1704.01701zbMath1473.68134arXiv1704.01701MaRDI QIDQ115375

Daniel Alabi, Margo Seltzer, Elaine Angelino, Cynthia Rudin, Nicholas Larus-Stone, Nicholas Larus-Stone, Cynthia Rudin, Margo Seltzer, Daniel Alabi, Elaine Angelino

Publication date: 6 April 2017

Full work available at URL: https://arxiv.org/abs/1704.01701

zbMATH Keywords

optimizationdecision treesinterpretable modelsrule listscriminal justice applications

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to social sciences (62P25) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (20)

Learning Optimized Risk Scores ⋮ Efficient Learning of Interpretable Classification Rules ⋮ Leveraging integer linear programming to learn optimal fair rule lists ⋮ Causal Rule Sets for Identifying Subgroups with Enhanced Treatment Effects ⋮ SAT-based optimal classification trees for non-binary data ⋮ The explanation game: a formal framework for interpretable machine learning ⋮ Logic explained networks ⋮ Improving fairness generalization through a sample-robust optimization method ⋮ Visualizing the Implicit Model Selection Tradeoff ⋮ Considerations when learning additive explanations for black-box models ⋮ SIRUS: stable and interpretable RUle set for classification ⋮ Learning customized and optimized lists of rules with mathematical programming ⋮ Unnamed Item ⋮ corels ⋮ Interpretable machine learning: fundamental principles and 10 grand challenges ⋮ Unnamed Item ⋮ Robust subgroup discovery. Discovering subgroup lists using MDL ⋮ Unnamed Item ⋮ Learning Optimal Decision Sets and Lists with SAT ⋮ SAT-based rigorous explanations for decision lists

Uses Software

• BayesTree
• C4.5
• ORL
• CMAR
• BartPy

Cites Work

• BART: Bayesian additive regression trees
• Supersparse linear integer models for optimized medical scoring systems
• Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
• To explain or to predict?
• Finding a short and accurate decision rule in disjunctive normal form by exhaustive search
• Very simple classification rules perform well on most commonly used datasets
• An experimental evaluation of simplicity in rule learning
• Using decision lists to construct interpretable and parsimonious treatment regimes
• A Bayesian CART algorithm
• A Computational Study of Search Strategies for Mixed Integer Programming
• Bayesian treed models
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Learning Certifiably Optimal Rule Lists for Categorical Data