Fast Effective Rule Induction

By William W. Cohen. 1995

Subfields: Statistical Learning Theory, Algorithms & Complexity

How researchers see this paper

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

In Statistical Learning Theory

In Algorithms & Complexity

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, methodology): “Associative classification methods assemble decision lists or decision sets from a set of pre-mined rules, generally either by greedily adding rules to the model one by one, or simply including all “top-scoring” rules into a decision set, where each rule is scored separately according to a scoring f”
Interpretable Two-level Boolean Rule Learning for Classification (2015, neutral): “Keywords Interpretable Classifier, Linear Programming Relaxation”
Learning Certifiably Optimal Rule Lists (2017, methodology): “The RIPPER algorithm (Cohen, 1995) is similar to the Bayesian tree methods in that it grows, prunes, and then locally optimizes.”
Computing Optimal Decision Sets with SAT (2020, methodology): “et of instances and the quality of solutions i terms of decision set size. A number of state-of-the-art algorithms were additionally considered including the heuristic methods CN2 [11,12], and RIPPER [13], as well as MaxSAT-based IMLI [20] (which is a direct successor of MLIC [39]). The implementati”
IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules (2019, methodology): “We observe that rule size of IMLI is signiﬁcantly smaller than that of RIPPER and MLIC .”
Learning customized and optimized lists of rules with mathematical programming (2018, methodology): “Experiments ofWang and Rudin [70], Yang et al. [73] found that the performance of inductive rule learner RIPPER [16]wasworse than that of othermethods; rule learningmethods generally do not aim to achieve or prove optimality.”
MLIC: A MaxSAT-Based Framework for Learning Interpretable Classification Rules (2018, background): “There is a long history of learning interpretable classification models from data, including popular approaches such as decision trees [5,29], decision lists [30], and classification rules [10].”
Boolean Decision Rules via Column Generation (2018, methodology): “Predominant practical approaches include a covering or separate-and-conquer strategy ([15, 14, 16, 26, 28, 40],”
An optimization approach to learning falling rule lists (2017, methodology): “the RIPPERk algorithm (Cohen, 1995) and the CBA algorithm (Liu et al.”
Scalable Bayesian Rule Lists (2016, methodology): “Rule learning algorithms have been developed possibly since the AQ algorithm in the 1960s (Michalski, 1969) and throughout the 1980’s and 90’s (Cendrowska, 1987; Quinlan, 1983; Clark & Niblett, 1989; Cohen, 1995; Liu, Hsu, & Ma, 1998).”
Learning Optimized Or's of And's (2015, methodology): “…1998; Han, Pei, and Yin, 2000; Li, Han, and Pei, 2001; Yin and Han, 2003; Chen et al., 2006; Cheng et al., 2007), and rule induction methods (e.g., Cohen, 1995), there has been little in the way of algorithms designed for applications where cognitive simplicity is first and foremost (with some…”
Learning Explainable Decision Rules via Maximum Satisfiability (2020, methodology): “We only considered RIPPER after relinquishing our rights to the HBA dataset, wherefore its entry is missing for the HBA dataset.”
SMOTE: Synthetic Minority Over-sampling Technique (2002, methodology): “5 decision tree classifier (Quinlan, 1992), Ripper (Cohen, 1995b), and a Naive Bayes Classifier show that our approach improves over other previous re-sampling, modifying loss ratio, and class priors approaches, using either the AUC or ROC convex hull.”
Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems (2015, methodology): “The decision tree methods are representatives of the class of greedy and heuristic methods (e.g., [10,11,13,16,17,26–28, 31, 37, 38 , 51 ] ) that”
CPAR: Classification based on Predictive Association Rules (2003, background): “Table 1: Accuracy: C4.5, RIPPER, CBA, CMAR and CPAR differ a lot, and the arithmetic average is dominated by the most time-consuming datasets.”
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, neutral): “Decision sets (also known as rule sets) also enjoy a long history of optimization techniques, ranging from Frank and Witten [1998], Cohen [1995], Clark and Boswell [1991] to Lakkaraju et al. [2016].”
Finding a short and accurate decision rule in disjunctive normal form by exhaustive search (2010, methodology): “Our results indicate that EXPLORE is not very sensitive to overfitting, since only for the vote dataset it induced a longer rule than RIPPER and SL2, with a lower performance.”
Transfer Learning for Reinforcement Learning Domains: A Survey (2009, methodology): “Similar to strategy transfer, Taylor and Stone (2007b) learnruleswith RIPPER (Cohen, 1995) that summarize a learned source task policy.”
Automated severity assessment of software defect reports (2008, methodology): “The learner used here was a JAVA version of Cohen’s RIPPER rule learner [7].”