Fuzzy Clustering in Classification Using Weighted Features

This paper proposes a fuzzy classification/regression method based on an extension of classical fuzzy clustering algorithms, by weighting the features during cluster estimation. By translating the importance of each feature using weights, the classifier can lead to better results. The proposed method is applied to target selection, where the goal is to maximize profit obtained from the clients. A real-world application shows the effectiveness of the proposed approach.

[1]  Uzay Kaymak,et al.  Fuzzy Decision Making , 2002 .

[2]  Donald Gustafson,et al.  Fuzzy clustering with a fuzzy covariance matrix , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[3]  J. S. Cramer,et al.  The Logit Model: An Introduction for Economists , 1991 .

[4]  C. Bauer.  A direct mail customer purchase model , 1988 .

[5]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[6]  Uzay Kaymak,et al.  Fuzzy Decision Making in Modeling and Control , 2002, World Scientific Series in Robotics and Intelligent Systems.

[7]  U. Kaymak.  Fuzzy target selection using RFM variables , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[8]  Joao M. C. Sousa,et al.  Comparison of target selection methods in direct marketing , 2002 .

[9]  Uzay Kaymak,et al.  A comparative study of fuzzy target selection methods in direct marketing , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[10]  Uzay Kaymak,et al.  Fuzzy clustering with volume prototypes and adaptive cluster merging , 2002, IEEE Trans. Fuzzy Syst..