Post-Analysis of Learned Rules

By B. Liu, Wynne Hsu. 1996

How researchers see this paper

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

Citations in the corpus

Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking (2017, background): “her line of research on actionable knowledge discovery concerns post-processing techniques. Liu etal.propose methods for pruning and summarizing learned rules, as well as matching rules by similarity [14, 15]. Cao etal.present domain-driven data mining; a paradigm shi› from a research-centered disci”
Integrating Classification and Association Rule Mining (1998, background): “Techniques such as those in (Liu and Hsu 1996; Liu, Hsu and Chen 1997) can be employed to help the user identify understandable rules.”
Flexible Frameworks for Actionable Knowledge Discovery (2010, methodology): “Additionally, rather than addressing the whole KDD process as it did in some of related works, this paper only focuses on method/algorithm frameworks toward AKD.”
Pruning and summarizing the discovered associations (1999, background): “In subjective interestingness research in data mining, [22, 11, 12, 19] proposed a number of methods for finding unexpected rules.”
Segmentation (2019, unknown): “Patterns are often deemed \interesting" on the basis of their con dence and support [1], information content [24], and unexpectedness [17, 23].”
Detecting Group Differences: Mining Contrast Sets (2001, background): “Another technique is to compare the discovered rules to an explicit list of rules or beliefs that the user already knows (Liu and Hsu, 1996; Liu et al., 1997; Padmanabhan and Tuzhilin, 1998; Silberschatz and Tuzhilin, 1996; Liu et al., 1999b) and then to show only those results that are unexpected.”
DATA MINING TECHNIQUES (2003, background): “Other approaches to the interestingness of rules include rule templates [44], which limits rules to only those fitting a template; minimal rule cover [77], which eliminates rules already implied by other rules; and “unexpectedness” [51, 74].”
Optimal Action Extraction for Random Forests and Boosted Trees (2015, methodology): “Liu et al. tried to discover actionable knowledge by pruning and summarizing the learnt rules, as well as matching rules by similarity [21, 22].”