Conference proceeding
Sharing classifiers among ensembles from related problem domains
Fifth IEEE International Conference on Data Mining (ICDM'05), pp.8 pp-529
2005
DOI: 10.1109/ICDM.2005.131
Abstract
A classification ensemble is a group of classifiers that all solve the same prediction problem in different ways. It is well-known that combining the predictions of classifiers within the same problem domain using techniques like bagging or boosting often improves the performance. This research shows that sharing classifiers among different but closely related problem domains can also be helpful. In addition, a semi-definite programming based ensemble pruning method is implemented in order to optimize the selection of a subset of classifiers for each problem domain. Computational results on a catalog dataset indicate that the ensembles resulting from sharing classifiers among different product categories generally have larger AUCs than those ensembles trained only on their own categories. The pruning algorithm not only prevents the occasional decrease of effectiveness caused by conflicting concepts among the problem domains, but also provides a better understanding of the problem domains and their relationships.
Details
- Title: Subtitle
- Sharing classifiers among ensembles from related problem domains
- Creators
- Yi Zhang - Dept. of Manage. Sci., Iowa Univ., IA, USAW.N. Street - Dept. of Manage. Sci., Iowa Univ., IA, USAS. Burer - Dept. of Manage. Sci., Iowa Univ., IA, USA
- Resource Type
- Conference proceeding
- Publication Details
- Fifth IEEE International Conference on Data Mining (ICDM'05), pp.8 pp-529
- Publisher
- IEEE
- DOI
- 10.1109/ICDM.2005.131
- ISSN
- 1550-4786
- eISSN
- 2374-8486
- Language
- English
- Date published
- 2005
- Academic Unit
- Bus Admin College; Nursing; Computer Science; Business Analytics
- Record Identifier
- 9984380419502771
Metrics
1 Record Views