Go to:
Logótipo
Você está em: Start > Publications > View > Optimal leverage association rules with numerical interval conditions
Publication

Optimal leverage association rules with numerical interval conditions

Title
Optimal leverage association rules with numerical interval conditions
Type
Article in International Scientific Journal
Year
2012
Authors
Alipio Mario Jorge
(Author)
FCUP
View Personal Page You do not have permissions to view the institutional email. Search for Participant Publications View Authenticus page Without ORCID
Paulo J Azevedo
(Author)
Other
The person does not belong to the institution. The person does not belong to the institution. The person does not belong to the institution. View Authenticus page Without ORCID
Journal
Vol. 16 No. 1
Pages: 25-47
ISSN: 1088-467X
Publisher: IOS PRESS
Indexing
Publicação em ISI Web of Knowledge ISI Web of Knowledge - 0 Citations
Publicação em ISI Web of Science ISI Web of Science
Scientific classification
CORDIS: Physical sciences > Computer science > Cybernetics > Artificial intelligence
FOS: Natural sciences > Computer and information sciences
Other information
Authenticus ID: P-002-H3N
Resumo (PT): Neste trabalho, propomos uma estrutura para definir e descobrir regras de associação ótimas envolvendo um atributo numérico A no conseqüente. O consequente tem a forma de condições de intervalo (A, A ⩾ X ou A ∈ I onde I é um intervalo ou um conjunto de intervalos de forma [x_l, x_u)). A otimização é com relação à leverage, uma conhecida medida de interesse das regras de associação As regras geradas são chamadas de regras de leverage máximas (MLR) e são gerados a partir de regras de distribuição. O princípio para encontrar o MLR está relacionada com o teste de Kolmogorov-Smirnov. Propomos diferentes métodos para a geração de MLR, tendo em conta optimalidade da leverage e legibilidade. Nós demonstramos teoricamente a otimalidade dos principais métodos exatos, e medimos a perda de influência dos métodos aproximados. Mostramos empiricamente que o processo de descoberta é escalável.
Abstract (EN): In this paper we propose a framework for defining and discovering optimal association rules involving a numerical attribute A in the consequent. The consequent has the form of interval conditions (A < x, A >= x or A is an element of I where I is an interval or a set of intervals of the form [x(l), x(u))). The optimality is with respect to leverage, one well known association rule interest measure. The generated rules are called Maximal Leverage Rules (MLR) and are generated from Distribution Rules. The principle for finding the MLR is related to the Kolmogorov-Smirnov goodness of fit statistical test. We propose different methods for MLR generation, taking into account leverage optimallity and readability. We theoretically demonstrate the optimality of the main exact methods, and measure the leverage loss of approximate methods. We show empirically that the discovery process is scalable.
Language: English
Type (Professor's evaluation): Scientific
No. of pages: 23
Documents
We could not find any documents associated to the publication.
Related Publications

Of the same authors

Iterative reordering of rules for building ensembles without relearning (2007)
Chapter or Part of a Book
Paulo J Azevedo; Alipio M Jorge
Comparing rule measures for predictive association rules (2007)
Chapter or Part of a Book
Paulo J Azevedo; Alipio M Jorge
Visual interactive subgroup discovery with numerical properties of interest (2006)
Article in International Scientific Journal
Alipio M Jorge; Fernando Pereira; Paulo J Azevedo
Ensembles of jittered association rule classifiers (2010)
Article in International Scientific Journal
Paulo J Azevedo; Alipio Mario Jorge
Distribution rules with numeric attributes of interest (2006)
Article in International Scientific Journal
Alipio M Jorge; Paulo J Azevedo; Fernando Pereira

Of the same scientific areas

Web mining for the integration of data mining with business intelligence in web-based decision support systems (2014)
Chapter or Part of a Book
Marcos Aurélio Domingues; Alípio M. Jorge; Carlos Soares; Solange Oliveira Rezende
Using Multivariate Adaptive Regression Splines in the Construction of Simulated Soccer Team's Behavior Models (2013)
Article in International Scientific Journal
Pedro Henriques Abreu; Daniel Castro Silva; Joao Mendes Moreira; Luis Paulo Reis; Julio Garganta
Improving the accuracy of long-term travel time prediction using heterogeneous ensembles (2015)
Article in International Scientific Journal
Joao Mendes Moreira; Alipio Mario Jorge; Jorge Freire de Sousa; Carlos Soares
Improving a simulated soccer team's performance through a Memory-Based Collaborative Filtering approach (2014)
Article in International Scientific Journal
Pedro Henriques Abreu; Daniel Castro Silva; Fernando Almeida; João Mendes-Moreira

See all (56)

Of the same journal

Ubiquitous Knowledge Discovery Introduction (2011)
Another Publication in an International Scientific Journal
João Gama; May, M
Mining official data (2003)
Another Publication in an International Scientific Journal
brito, p; malerba, d
Knowledge discovery from data streams (2008)
Another Publication in an International Scientific Journal
João Gama; Aguilar Ruiz, J; Klinkenberg, R
Knowledge discovery from data streams (2007)
Another Publication in an International Scientific Journal
João Gama; Aguilar Ruiz, J
Incremental learning and concept drift: Editor's introduction (2004)
Another Publication in an International Scientific Journal
Kubat, M; João Gama; Utgoff, P

See all (39)

Recommend this page Top
Copyright 1996-2024 © Faculdade de Arquitectura da Universidade do Porto  I Terms and Conditions  I Acessibility  I Index A-Z  I Guest Book
Page created on: 2024-11-08 at 21:21:31 | Acceptable Use Policy | Data Protection Policy | Complaint Portal