Algorithms for Attribute Selection and Knowledge Discovery

The features relevant selection is a task performed prior to the data mining and can be seen as one of the most important problems to solve in the data preprocessing stage an in the machine learning. With the feature selection is mainly intended to improve predictive or descriptive performance of mo...

Full description

Saved in:
Bibliographic Details
Published inKnowledge Management in Organizations pp. 399 - 409
Main Authors Rodríguez R., Jorge Enrique, García, Víctor Hugo Medina, Estrada, Lina María Medina
Format Book Chapter
LanguageEnglish
Published Cham Springer International Publishing
SeriesCommunications in Computer and Information Science
Subjects
Complexity
Data mining
Decision trees
Entropy
Estimation of distribution algorithms
Features selection
Machine learning
Online AccessGet full text

Cover

More Information
Summary:The features relevant selection is a task performed prior to the data mining and can be seen as one of the most important problems to solve in the data preprocessing stage an in the machine learning. With the feature selection is mainly intended to improve predictive or descriptive performance of models and implement faster and less expensive algorithms. In this paper an analysis about feature selection methods is made emphasizing on decision trees, entropy measure for ranking features, and estimation of distribution algorithms. Finally, we show the result analysis of execute the three algorithms.
ISBN:9783319626970
3319626973
ISSN:1865-0929
1865-0937
DOI:10.1007/978-3-319-62698-7_33