Ponencia
A post-processing strategy for SVM learning from unbalanced data
Autor/es | Núñez Castro, Haydemar
González Abril, Luis Angulo Bahón, Cecilio |
Departamento | Universidad de Sevilla. Departamento de Economía Aplicada I |
Fecha de publicación | 2011 |
Fecha de depósito | 2018-11-05 |
Publicado en |
|
ISBN/ISSN | 978-2-87419-044-5 |
Resumen | Standard learning algorithms may perform poorly when learning from unbalanced datasets. Based on the Fisher’s discriminant analysis, a post-processing strategy is introduced to deal datasets with significant imbalance in ... Standard learning algorithms may perform poorly when learning from unbalanced datasets. Based on the Fisher’s discriminant analysis, a post-processing strategy is introduced to deal datasets with significant imbalance in the data distribution. A new bias is defined, which reduces skew towards the minority class. Empirical results from experiments for a learned SVM model on twelve UCI datasets indicates that the proposed solution improves the original SVM, and they also improve those reported when using a z-SVM, in terms of g-mean and sensitivity. |
Agencias financiadoras | Ministerio de Ciencia y Tecnología (MCYT). España |
Identificador del proyecto | TIN2009-14378-C02-01 |
Cita | Núñez Castro, H., González Abril, L. y Angulo Bahón, C. (2011). A post-processing strategy for SVM learning from unbalanced data. En 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (195-200), Bruges: Ciaco. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
A post-processing strategy.pdf | 101.9Kb | [PDF] | Ver/ | |