Feature Selection in Marketing Applications

Authors:
Stefan Lessmann;Stefan Voß
Affiliations:
Institute of Information Systems, University of Hamburg, Hamburg, Germany D-20146;Institute of Information Systems, University of Hamburg, Hamburg, Germany D-20146
Venue:
ADMA '09 Proceedings of the 5th International Conference on Advanced Data Mining and Applications
Year:
2009

Citing 12
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
An introduction to variable and feature selection

The Journal of Machine Learning Research
Ranking a random feature for variable and feature selection

The Journal of Machine Learning Research
Customer Targeting: A Neural Network Approach Guided by Genetic Algorithms

Management Science
A Modified Finite Newton Method for Fast Solution of Large Scale Linear SVMs

The Journal of Machine Learning Research
Training linear SVMs in linear time

Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
An introduction to ROC analysis

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
Benchmarking Classification Models for Software Defect Prediction: A Proposed Framework and Novel Findings

IEEE Transactions on Software Engineering
Feature selection in MLPs and SVMs based on maximum output information

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper is concerned with marketing applications of classification analysis. Feature selection (FS) is crucial in this domain to avoid cognitive overload of decision makers through use of excessively large attribute sets. Whereas algorithms for feature ranking have received considerable attention within the literature, a clear strategy how a subset of attributes should be selected once a ranking has been obtained is yet missing. Consequently, three candidate FS procedures are presented and contrasted by means of empirical experimentation on real-world data. The results offer some guidance which approach should be employed in practical applications and identify promising avenues for future research.