Skip to content

Prepending

Prepending is a generic strategy for decision list learning that has lower computation and develops shorter decision lists than the classical approach, without any general increase in prediction error.

Publications

Alternative Strategies for Decision List Construction.
Newlands, D. A., & Webb, G. I.
Proceedings of the Fourth International Conference on Data Mining (DATA MINING IV), Southampton, UK, pp. 265-273, 2004.
[Bibtex] [Abstract]  → Download PDF

@InProceedings{NewlandsWebb04a,
author = {Newlands, D. A. and Webb, G. I.},
booktitle = {Proceedings of the Fourth International Conference on Data Mining (DATA MINING IV)},
title = {Alternative Strategies for Decision List Construction},
year = {2004},
address = {Southampton, UK},
editor = {Ebecken, N.F.F.E. and Brebbia, C.A. and Zanasi, A.},
pages = {265-273},
publisher = {WIT Press},
abstract = {This work surveys well-known approaches to building decision lists. Some novel variations to strategies based on default rules for the most common class and insertion of new rules before the default rule are presented. These are expected to offer speed up in the construction of the decision list as well as compression of the length of the list. These strategies and a testing regime have been implemented and some empirical studies done to compare the strategies. Experimental results are presented and interpreted. We show that all strategies deliver decision lists of comparable accuracy. However, two techniques are shown to deliver this accuracy with lists composed of significantly fewer rules than alternative strategies. Of these, one also demonstrates significant computational advantages. The prepending strategy is also demonstrated to produce decision lists which are as much as an order of magnitude shorter than those produced by CN2.},
audit-trail = {Paper posted on web 9/8/04},
keywords = {Prepend},
location = {Rio de Janeiro, Brazil},
related = {prepending},
}
ABSTRACT This work surveys well-known approaches to building decision lists. Some novel variations to strategies based on default rules for the most common class and insertion of new rules before the default rule are presented. These are expected to offer speed up in the construction of the decision list as well as compression of the length of the list. These strategies and a testing regime have been implemented and some empirical studies done to compare the strategies. Experimental results are presented and interpreted. We show that all strategies deliver decision lists of comparable accuracy. However, two techniques are shown to deliver this accuracy with lists composed of significantly fewer rules than alternative strategies. Of these, one also demonstrates significant computational advantages. The prepending strategy is also demonstrated to produce decision lists which are as much as an order of magnitude shorter than those produced by CN2.

Recent Progress in Learning Decision Lists by Prepending Inferred Rules.
Webb, G. I.
Proceedings of the Second Singapore International Conference on Intelligent Systems (SPICIS-94), Singapore, pp. 280-285, 1994.
[Bibtex] [Abstract]  → Download PDF

@InProceedings{Webb94a,
author = {Webb, G. I.},
booktitle = {Proceedings of the Second Singapore International Conference on Intelligent Systems (SPICIS-94)},
title = {Recent Progress in Learning Decision Lists by Prepending Inferred Rules},
year = {1994},
address = {Singapore},
pages = {280-285},
publisher = {{Asia} Computer Weekly},
volume = {B},
abstract = {This paper describes a new algorithm for learning decision lists that operates by prepending successive rules to the front of the list under construction. By contrast, the classic algorithm operates by appending successive rules to the end of the decision list under construction. The new algorithm is demonstrated in the majority of cases to produce smaller classifiers that provide improved predictive accuracy in less time than the classic algorithm.},
keywords = {Rule Learning and Prepend},
location = {Singapore},
related = {prepending},
}
ABSTRACT This paper describes a new algorithm for learning decision lists that operates by prepending successive rules to the front of the list under construction. By contrast, the classic algorithm operates by appending successive rules to the end of the decision list under construction. The new algorithm is demonstrated in the majority of cases to produce smaller classifiers that provide improved predictive accuracy in less time than the classic algorithm.

Learning Decision Lists by Prepending Inferred Rules.
Webb, G. I., & Brkic, N.
Proceedings of the AI 93 Workshop on Machine Learning and Hybrid Systems, pp. 6-10, 1993.
[Bibtex] [Abstract]  → Download PDF

@InProceedings{WebbBrkic93,
Title = {Learning Decision Lists by Prepending Inferred Rules},
Author = {Webb, G. I. and Brkic, N.},
Booktitle = {Proceedings of the AI 93 Workshop on Machine Learning and Hybrid Systems},
Year = {1993},
Editor = {Sestito, S.},
Pages = {6-10},
Abstract = {This paper describes a new algorithm for learning decision lists that operates by prepending successive rules to front of the list under construction. This contrasts with the original decision list induction algorithm which operates by appending successive rules to end of the list under construction. The new algorithm is demonstrated in the majority of cases to produce smaller classifiers that provide improved predictive accuracy than those produced by the original decision list induction algorithm.},
Keywords = {Prepend and Rule Learning},
Location = {Melbourne, Australia},
Related = {prepending}
}
ABSTRACT This paper describes a new algorithm for learning decision lists that operates by prepending successive rules to front of the list under construction. This contrasts with the original decision list induction algorithm which operates by appending successive rules to end of the list under construction. The new algorithm is demonstrated in the majority of cases to produce smaller classifiers that provide improved predictive accuracy than those produced by the original decision list induction algorithm.