APRIORI Algorithm for Label Ranking

• Tipo: Tese
• Data: 2010

Autores

Cláudio Sá (Autor) FEP; Carlos Soares (Coordenador) FEP; Joaquim Costa (Coordenador) FEP

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da computação e da informação

CORDIS: Ciências Físicas > Ciência de computadores ; Ciências Físicas > Matemática > Algoritmos ; Ciências Físicas > Matemática > Matemática computacional

Instituições Associadas

FC - Faculdade de Ciências da Universidade do Porto

Outras Informações

Abstract (EN): Label ranking studies a problem of learning a mapping from instances to rankings over a finite number of predefined labels. Recently, a number of learning algorithms have been adapted for label ranking, including instance-based and tree-based methods. We continue this line of work by proposing an adaptation of association rules for label ranking based on the APRIORI algorithm. To achieve this, the algorithm mainly needs two changes. The first one consists on adapting the support and confidence measures. The second adaptation is the development of a method to use the rules to make predictions for new examples. Additionally we propose a simple greedy method to select the parameters of the algorithm. We tested the new algorithm on benchmark problems. Despite the simplicity of the approach, the results clearly show that the method is competitive with state-of-the-art label ranking algorithms.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 50