Finding Probabilistic Rule Lists using the Minimum Description Length Principle
(2018) 21st International Conference on Discovery Science (DS 2018) — Location: Limassol, Cyprus (29.October.2018)
Files
paper_20.pdf
Open Access - Adobe PDF
- 414.48 KB
Details
- Authors
- Abstract
- An important task in data mining is that of rule discovery in supervised data. Well-known examples include rule-based classification and subgroup discovery. Motivated by the need to succinctly describe an entire labeled dataset, rather than accurately classify the label, we propose an MDL-based supervised rule discovery task. The task concerns the discovery of a small rule list where each rule captures the probability of the Boolean target attribute being true. Our approach is built on a novel combination of two main building blocks: (i) the use of the Minimum Description Length (MDL) principle to characterize good-and- small sets of probabilistic rules, (ii) the use of branch-and-bound with a best-first search strategy to find better-than-greedy and optimal solutions for the proposed task. We experimentally show the effectiveness of our approach, by providing a comparison with other supervised rule learning algorithms on real-life datasets.
- Affiliations
Citations
Aoga, J., Guns, T., Nijssen, S., & Schaus, P. (2018). Finding Probabilistic Rule Lists using the Minimum Description Length Principle. Discovery Science 21th International Conference, DS 2018, Limassol, Cyprus, October 29–31, 2018, Proceedings. Published. 21st International Conference on Discovery Science (DS 2018), Limassol, Cyprus. https://hdl.handle.net/2078.5/268121 (Original work published 2018)