Scalable Bayesian Rule Lists

Abstract

We present an algorithm for building probabilistic rule lists that is two orders of magnitude faster than previous work. Rule list algorithms are competitors for decision tree algorithms. They are associative classifiers, in that they are built from pre-mined association rules. They have a logical structure that is a sequence of IF-THEN rules, identical to a decision list or one-sided decision tree. Instead of using greedy splitting and pruning like decision tree algorithms, we fully optimize over rule lists, striking a practical balance between accuracy, interpretability, and computational speed. The algorithm presented here uses a mixture of theoretical bounds (tight enough to have practical implications as a screening or bounding procedure), computational reuse, and highly tuned language libraries to achieve computational efficiency. Currently, for many practical problems, this method achieves better accuracy and sparsity than decision trees; further, in many cases, the computational time is practical and often less than that of decision trees. The result is a probabilistic classifier (which estimates P(y = 1|x) for each x) that optimizes the posterior of a Bayesian hierarchical model over rule lists.

31 pages, 19 figures

References in corpus (5)

• Predictive learning via rule ensembles
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• Bayesian hierarchical rule modeling for predicting medical conditions
• Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems
• Using Decision Lists to Construct Interpretable and Parsimonious Treatment Regimes

Cited by in corpus (5)

• A Survey on the Explainability of Supervised Machine Learning
• The Authority of "Fair" in Machine Learning
• Using Program Induction to Interpret Transition System Dynamics
• Explaining Transition Systems through Program Induction
• ACDC: $\alpha$-Carving Decision Chain for Risk Stratification