LNCS 2810 APRIORI SD Adapting Association Rule
Learning to Subgroup Discovery 1st Edition by
Branko KavÅ¡ek, Nada LavraÄ■, Viktor JovanoskiÂ
ISBN 3540452311 9783540452317 pdf download
https://ebookball.com/product/lncs-2810-apriori-sd-adapting-
association-rule-learning-to-subgroup-discovery-1st-edition-by-
branko-kava-ek-nada-lavraa-viktor-jovanoski-
isbn-3540452311-9783540452317-12792/
Explore and download more ebooks or textbooks
at ebookball.com
, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats
Introduction To 80 86 Assembly Language And Computer Architecture 1st
Edition by Detmer ISBN 0763717738 9780763717735
https://ebookball.com/product/introduction-to-80-86-assembly-
language-and-computer-architecture-1st-edition-by-detmer-
isbn-0763717738-9780763717735-12404/
Introduction to 80 86 Assembly Language and Computer Architecture 1st
Edition by Richard C Detmer ISBN 0763746622 9780763746629
https://ebookball.com/product/introduction-to-80-86-assembly-
language-and-computer-architecture-1st-edition-by-richard-c-
detmer-isbn-0763746622-9780763746629-9016/
Machine Learning for Cybersecurity Cookbook Over 80 recipes on how to
implement machine learning algorithms for building security systems
using Python 1st edition by Emmanuel Tsukerman 9781838556341
1838556346
https://ebookball.com/product/machine-learning-for-cybersecurity-
cookbook-over-80-recipes-on-how-to-implement-machine-learning-
algorithms-for-building-security-systems-using-python-1st-
edition-by-emmanuel-tsukerman-9781838556341-1/
LNCS 2810 Pruning for Monotone Classification Trees 1st Edition by Ad
Feelders, Martijn Pardoel ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-pruning-for-monotone-
classification-trees-1st-edition-by-ad-feelders-martijn-pardoel-
isbn-3540452311-9783540452317-14426/
,LNCS 2810 Classification of Protein Localisation Patterns via
Supervised Neural Network Learning 1st Edition by Aristoklis
Anastasiadis, George Magoulas, Xiaohui Liu ISBN 3540452311
9783540452317
https://ebookball.com/product/lncs-2810-classification-of-
protein-localisation-patterns-via-supervised-neural-network-
learning-1st-edition-by-aristoklis-anastasiadis-george-magoulas-
xiaohui-liu-isbn-3540452311-9783540452317-13568/
LNCS 2810 A Novel Partial Memory Learning Algorithm Based on Grey
Relational Structure 1st Edition by Chi Chun Huang, Hahn Ming LeeÂ
ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-a-novel-partial-memory-
learning-algorithm-based-on-grey-relational-structure-1st-
edition-by-chi-chun-huang-hahn-ming-lee-
isbn-3540452311-9783540452317-11962/
LNCS 2810 A Semi supervised Method for Learning the Structure of
Robot Environment Interactions 1st Edition by Axel Grobmann, Matthias
Wendt, Jeremy Wyatt ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-a-semi-supervised-method-
for-learning-the-structure-of-robot-environment-interactions-1st-
edition-by-axel-grobmann-matthias-wendt-jeremy-wyatt-
isbn-3540452311-9783540452317-13436/
LNCS 2810 Measures of Rule Quality for Feature Selection in Text
Categorization 1st Edition by Elena Montañés, Javier Fernández,
Irene DÃ-az, ElÃ-as Combarro, José Ranilla ISBN 3540452311
9783540452317
https://ebookball.com/product/lncs-2810-measures-of-rule-quality-
for-feature-selection-in-text-categorization-1st-edition-by-
elena-montaa-a-c-s-javier-ferna-ndez-irene-daaz-elaas-combarro-
josa-c-ranilla-isbn-3540452311-97835404523/
LNCS 2810 Compression Technique Preserving Correlations of a
Multivariate Temporal Sequence 1st Edition by Ahlame Chouakria
Douzal ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-compression-technique-
preserving-correlations-of-a-multivariate-temporal-sequence-1st-
edition-by-ahlame-chouakria-douzal-
isbn-3540452311-9783540452317-14220/
, APRIORI-SD: Adapting Association Rule
Learning to Subgroup Discovery
Branko Kavšek, Nada Lavrač, and Viktor Jovanoski
Institute Jožef Stefan, Jamova 39, 1000 Ljubljana, Slovenia
{branko.kavsek,nada.lavrac,}
Abstract. This paper presents a subgroup discovery algorithm
APRIORI-SD, developed by adapting association rule learning to sub-
group discovery. This was achieved by building a classification rule
learner APRIORI-C, enhanced with a novel post-processing mechanism,
a new quality measure for induced rules (weighted relative accuracy) and
using probabilistic classification of instances. Results of APRIORI-SD
are similar to the subgroup discovery algorithm CN2-SD while experi-
mental comparisons with CN2, RIPPER and APRIORI-C demonstrate
that the subgroup discovery algorithm APRIORI-SD produces substan-
tially smaller rule sets, where individual rules have higher coverage and
significance.
1 Introduction
Classical rule learning algorithms are designed to construct classification and
prediction rules [12,3,4,7]. In addition to this area of machine learning, referred
to as supervised learning or predictive induction, developments in descriptive
induction have recently gained much attention, in particular association rule
learning [1] (e.g., the APRIORI association rule learning algorithm), subgroup
discovery (e.g., the MIDOS subgroup discovery algorithm [18,5]), and other
approaches to non-classificatory induction.
As in the MIDOS approach, a subgroup discovery task can be defined as
follows: given a population of individuals and a property of those individuals
we are interested in, find population subgroups that are statistically ‘most in-
teresting’, e.g., are as large as possible and have the most unusual statistical
(distributional) characteristics with respect to the property of interest [18,5].
Some of the questions on how to adapt classical classification rule learning
approaches to subgroup discovery have already been addressed in [10] and a
well-known rule learning algorithm CN2 was adapted to subgroup discovery. In
this paper we take a rule learner APRIORI-C instead of CN2 and adapt it to
subgroup discovery, following the guidelines from [10].
We have implemented the new subgroup discovery algorithm APRIORI-SD
in C++ by modifying the APRIORI-C algorithm. The proposed approach per-
forms subgroup discovery through the following modifications of the rule learning
algorithm APRIORI-C: (a) using a weighting scheme in rule post-processing, (b)
using weighted relative accuracy as a new measure of the quality of the rules in
M.R. Berthold et al. (Eds.): IDA 2003, LNCS 2810, pp. 230–241, 2003.
c Springer-Verlag Berlin Heidelberg 2003
Learning to Subgroup Discovery 1st Edition by
Branko KavÅ¡ek, Nada LavraÄ■, Viktor JovanoskiÂ
ISBN 3540452311 9783540452317 pdf download
https://ebookball.com/product/lncs-2810-apriori-sd-adapting-
association-rule-learning-to-subgroup-discovery-1st-edition-by-
branko-kava-ek-nada-lavraa-viktor-jovanoski-
isbn-3540452311-9783540452317-12792/
Explore and download more ebooks or textbooks
at ebookball.com
, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats
Introduction To 80 86 Assembly Language And Computer Architecture 1st
Edition by Detmer ISBN 0763717738 9780763717735
https://ebookball.com/product/introduction-to-80-86-assembly-
language-and-computer-architecture-1st-edition-by-detmer-
isbn-0763717738-9780763717735-12404/
Introduction to 80 86 Assembly Language and Computer Architecture 1st
Edition by Richard C Detmer ISBN 0763746622 9780763746629
https://ebookball.com/product/introduction-to-80-86-assembly-
language-and-computer-architecture-1st-edition-by-richard-c-
detmer-isbn-0763746622-9780763746629-9016/
Machine Learning for Cybersecurity Cookbook Over 80 recipes on how to
implement machine learning algorithms for building security systems
using Python 1st edition by Emmanuel Tsukerman 9781838556341
1838556346
https://ebookball.com/product/machine-learning-for-cybersecurity-
cookbook-over-80-recipes-on-how-to-implement-machine-learning-
algorithms-for-building-security-systems-using-python-1st-
edition-by-emmanuel-tsukerman-9781838556341-1/
LNCS 2810 Pruning for Monotone Classification Trees 1st Edition by Ad
Feelders, Martijn Pardoel ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-pruning-for-monotone-
classification-trees-1st-edition-by-ad-feelders-martijn-pardoel-
isbn-3540452311-9783540452317-14426/
,LNCS 2810 Classification of Protein Localisation Patterns via
Supervised Neural Network Learning 1st Edition by Aristoklis
Anastasiadis, George Magoulas, Xiaohui Liu ISBN 3540452311
9783540452317
https://ebookball.com/product/lncs-2810-classification-of-
protein-localisation-patterns-via-supervised-neural-network-
learning-1st-edition-by-aristoklis-anastasiadis-george-magoulas-
xiaohui-liu-isbn-3540452311-9783540452317-13568/
LNCS 2810 A Novel Partial Memory Learning Algorithm Based on Grey
Relational Structure 1st Edition by Chi Chun Huang, Hahn Ming LeeÂ
ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-a-novel-partial-memory-
learning-algorithm-based-on-grey-relational-structure-1st-
edition-by-chi-chun-huang-hahn-ming-lee-
isbn-3540452311-9783540452317-11962/
LNCS 2810 A Semi supervised Method for Learning the Structure of
Robot Environment Interactions 1st Edition by Axel Grobmann, Matthias
Wendt, Jeremy Wyatt ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-a-semi-supervised-method-
for-learning-the-structure-of-robot-environment-interactions-1st-
edition-by-axel-grobmann-matthias-wendt-jeremy-wyatt-
isbn-3540452311-9783540452317-13436/
LNCS 2810 Measures of Rule Quality for Feature Selection in Text
Categorization 1st Edition by Elena Montañés, Javier Fernández,
Irene DÃ-az, ElÃ-as Combarro, José Ranilla ISBN 3540452311
9783540452317
https://ebookball.com/product/lncs-2810-measures-of-rule-quality-
for-feature-selection-in-text-categorization-1st-edition-by-
elena-montaa-a-c-s-javier-ferna-ndez-irene-daaz-elaas-combarro-
josa-c-ranilla-isbn-3540452311-97835404523/
LNCS 2810 Compression Technique Preserving Correlations of a
Multivariate Temporal Sequence 1st Edition by Ahlame Chouakria
Douzal ISBN 3540452311 9783540452317
https://ebookball.com/product/lncs-2810-compression-technique-
preserving-correlations-of-a-multivariate-temporal-sequence-1st-
edition-by-ahlame-chouakria-douzal-
isbn-3540452311-9783540452317-14220/
, APRIORI-SD: Adapting Association Rule
Learning to Subgroup Discovery
Branko Kavšek, Nada Lavrač, and Viktor Jovanoski
Institute Jožef Stefan, Jamova 39, 1000 Ljubljana, Slovenia
{branko.kavsek,nada.lavrac,}
Abstract. This paper presents a subgroup discovery algorithm
APRIORI-SD, developed by adapting association rule learning to sub-
group discovery. This was achieved by building a classification rule
learner APRIORI-C, enhanced with a novel post-processing mechanism,
a new quality measure for induced rules (weighted relative accuracy) and
using probabilistic classification of instances. Results of APRIORI-SD
are similar to the subgroup discovery algorithm CN2-SD while experi-
mental comparisons with CN2, RIPPER and APRIORI-C demonstrate
that the subgroup discovery algorithm APRIORI-SD produces substan-
tially smaller rule sets, where individual rules have higher coverage and
significance.
1 Introduction
Classical rule learning algorithms are designed to construct classification and
prediction rules [12,3,4,7]. In addition to this area of machine learning, referred
to as supervised learning or predictive induction, developments in descriptive
induction have recently gained much attention, in particular association rule
learning [1] (e.g., the APRIORI association rule learning algorithm), subgroup
discovery (e.g., the MIDOS subgroup discovery algorithm [18,5]), and other
approaches to non-classificatory induction.
As in the MIDOS approach, a subgroup discovery task can be defined as
follows: given a population of individuals and a property of those individuals
we are interested in, find population subgroups that are statistically ‘most in-
teresting’, e.g., are as large as possible and have the most unusual statistical
(distributional) characteristics with respect to the property of interest [18,5].
Some of the questions on how to adapt classical classification rule learning
approaches to subgroup discovery have already been addressed in [10] and a
well-known rule learning algorithm CN2 was adapted to subgroup discovery. In
this paper we take a rule learner APRIORI-C instead of CN2 and adapt it to
subgroup discovery, following the guidelines from [10].
We have implemented the new subgroup discovery algorithm APRIORI-SD
in C++ by modifying the APRIORI-C algorithm. The proposed approach per-
forms subgroup discovery through the following modifications of the rule learning
algorithm APRIORI-C: (a) using a weighting scheme in rule post-processing, (b)
using weighted relative accuracy as a new measure of the quality of the rules in
M.R. Berthold et al. (Eds.): IDA 2003, LNCS 2810, pp. 230–241, 2003.
c Springer-Verlag Berlin Heidelberg 2003
