The usage of descriptive data mining methods for predictive purposes is a recent trend in data mining research. It is well
motivated by the understandability of learned models, the limitation of the so-called “horizon effect” and by the fact thatit is a multi-task solution. In particular, associative classification, whose main idea is to exploit association rules discoveryapproaches in classification, gathered a lot of attention in recent years. A similar idea is represented by the use of emergingpatterns discovery for classification purposes. Emerging Patterns are classes of regularities whose support significantlychanges from one class to another and the main idea is to exploit class characterization provided by discovered emerging patternsfor class labeling. In this paper we propose and compare two distinct emerging patterns based classification approaches thatwork in the relational setting. Experiments empirically prove the effectiveness of both approaches and confirm the advantagewith respect to associative classification.
%0 Journal Article
%1 ceci08classification
%A Ceci, Michelangelo
%A Appice, Annalisa
%A Malerba, Donato
%D 2008
%J Database and Expert Systems Applications
%K research.mining
%P 283--296
%T Emerging Pattern Based Classification in Relational Data Mining
%U http://dx.doi.org/10.1007/978-3-540-85654-2_28
%X The usage of descriptive data mining methods for predictive purposes is a recent trend in data mining research. It is well
motivated by the understandability of learned models, the limitation of the so-called “horizon effect” and by the fact thatit is a multi-task solution. In particular, associative classification, whose main idea is to exploit association rules discoveryapproaches in classification, gathered a lot of attention in recent years. A similar idea is represented by the use of emergingpatterns discovery for classification purposes. Emerging Patterns are classes of regularities whose support significantlychanges from one class to another and the main idea is to exploit class characterization provided by discovered emerging patternsfor class labeling. In this paper we propose and compare two distinct emerging patterns based classification approaches thatwork in the relational setting. Experiments empirically prove the effectiveness of both approaches and confirm the advantagewith respect to associative classification.
@article{ceci08classification,
abstract = {The usage of descriptive data mining methods for predictive purposes is a recent trend in data mining research. It is well
motivated by the understandability of learned models, the limitation of the so-called “horizon effect” and by the fact thatit is a multi-task solution. In particular, associative classification, whose main idea is to exploit association rules discoveryapproaches in classification, gathered a lot of attention in recent years. A similar idea is represented by the use of emergingpatterns discovery for classification purposes. Emerging Patterns are classes of regularities whose support significantlychanges from one class to another and the main idea is to exploit class characterization provided by discovered emerging patternsfor class labeling. In this paper we propose and compare two distinct emerging patterns based classification approaches thatwork in the relational setting. Experiments empirically prove the effectiveness of both approaches and confirm the advantagewith respect to associative classification.},
added-at = {2009-06-30T19:01:49.000+0200},
author = {Ceci, Michelangelo and Appice, Annalisa and Malerba, Donato},
biburl = {https://www.bibsonomy.org/bibtex/2cbc7d6481f3df6b57fd0f24dc31ffcf1/msn},
description = {SpringerLink - Book Chapter},
interhash = {57fdd6f70417ca04c1bae70b0268ddd5},
intrahash = {cbc7d6481f3df6b57fd0f24dc31ffcf1},
journal = {Database and Expert Systems Applications},
keywords = {research.mining},
pages = {283--296},
timestamp = {2009-06-30T19:01:49.000+0200},
title = {Emerging Pattern Based Classification in Relational Data Mining},
url = {http://dx.doi.org/10.1007/978-3-540-85654-2_28},
year = 2008
}