A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity

Oguz Akbilgic, Hamparsum Bozdogan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, we introduce a new approach for supervised classification to handle mixed-data (i.e., categorical, binary, and continuous) data structures using a hybrid radial basis function neural networks (HRBF-NN). HRBF-NN supervised classification combines regression trees, ridge regression, and the genetic algorithm (GA) with radial basis function (RBF) neural networks (NN) along with information complexity (ICOMP) criterion as the fitness function to carry out both classification and subset selection of best predictors which discriminate between the classes. In this manner, we reduce the dimensionality of the data and at the same time improve classification accuracy of the fitted predictive model. We apply HRBFNN supervised classification to a real benchmark credit approval mixed-data set to classify the customers into good/bad classes for credit approval. Our results show the excellent performance of HRBF-NN method in supervised classification tasks.

Original languageEnglish (US)
Title of host publicationData Science, Learning by Latent Structures, and Knowledge Discovery
EditorsMatthias Bohmer, Sabine Krolak-Schwerdt, Berthold Lausen
PublisherKluwer Academic Publishers
Pages13-27
Number of pages15
Volume48
ISBN (Print)9783662449820
DOIs
StatePublished - Jan 1 2015
Event1st European Conference on Data Analysis, ECDA 2013 - Walferdange, Luxembourg
Duration: Jul 10 2013Jul 12 2013

Other

Other1st European Conference on Data Analysis, ECDA 2013
CountryLuxembourg
CityWalferdange
Period7/10/137/12/13

Fingerprint

Supervised Classification
Radial Basis Function Neural Network
Neural Network Model
Mixed Data
Neural networks
Regression Tree
Subset Selection
Ridge Regression
Predictive Model
Fitness Function
Categorical
Dimensionality
Predictors
Data Structures
Customers
Trees (mathematics)
Classify
Genetic Algorithm
Binary
Benchmark

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Analysis

Cite this

Akbilgic, O., & Bozdogan, H. (2015). A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity. In M. Bohmer, S. Krolak-Schwerdt, & B. Lausen (Eds.), Data Science, Learning by Latent Structures, and Knowledge Discovery (Vol. 48, pp. 13-27). Kluwer Academic Publishers. https://doi.org/10.1007/978-3-662-44983-7_2

A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity. / Akbilgic, Oguz; Bozdogan, Hamparsum.

Data Science, Learning by Latent Structures, and Knowledge Discovery. ed. / Matthias Bohmer; Sabine Krolak-Schwerdt; Berthold Lausen. Vol. 48 Kluwer Academic Publishers, 2015. p. 13-27.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Akbilgic, O & Bozdogan, H 2015, A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity. in M Bohmer, S Krolak-Schwerdt & B Lausen (eds), Data Science, Learning by Latent Structures, and Knowledge Discovery. vol. 48, Kluwer Academic Publishers, pp. 13-27, 1st European Conference on Data Analysis, ECDA 2013, Walferdange, Luxembourg, 7/10/13. https://doi.org/10.1007/978-3-662-44983-7_2
Akbilgic O, Bozdogan H. A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity. In Bohmer M, Krolak-Schwerdt S, Lausen B, editors, Data Science, Learning by Latent Structures, and Knowledge Discovery. Vol. 48. Kluwer Academic Publishers. 2015. p. 13-27 https://doi.org/10.1007/978-3-662-44983-7_2
Akbilgic, Oguz ; Bozdogan, Hamparsum. / A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity. Data Science, Learning by Latent Structures, and Knowledge Discovery. editor / Matthias Bohmer ; Sabine Krolak-Schwerdt ; Berthold Lausen. Vol. 48 Kluwer Academic Publishers, 2015. pp. 13-27
@inproceedings{5583ad0a5f224fe19e4c14a1f8474cd9,
title = "A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity",
abstract = "In this paper, we introduce a new approach for supervised classification to handle mixed-data (i.e., categorical, binary, and continuous) data structures using a hybrid radial basis function neural networks (HRBF-NN). HRBF-NN supervised classification combines regression trees, ridge regression, and the genetic algorithm (GA) with radial basis function (RBF) neural networks (NN) along with information complexity (ICOMP) criterion as the fitness function to carry out both classification and subset selection of best predictors which discriminate between the classes. In this manner, we reduce the dimensionality of the data and at the same time improve classification accuracy of the fitted predictive model. We apply HRBFNN supervised classification to a real benchmark credit approval mixed-data set to classify the customers into good/bad classes for credit approval. Our results show the excellent performance of HRBF-NN method in supervised classification tasks.",
author = "Oguz Akbilgic and Hamparsum Bozdogan",
year = "2015",
month = "1",
day = "1",
doi = "10.1007/978-3-662-44983-7_2",
language = "English (US)",
isbn = "9783662449820",
volume = "48",
pages = "13--27",
editor = "Matthias Bohmer and Sabine Krolak-Schwerdt and Berthold Lausen",
booktitle = "Data Science, Learning by Latent Structures, and Knowledge Discovery",
publisher = "Kluwer Academic Publishers",
address = "Netherlands",

}

TY - GEN

T1 - A new supervised classification of credit approval data via the hybridized RBF neural network model using information complexity

AU - Akbilgic, Oguz

AU - Bozdogan, Hamparsum

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In this paper, we introduce a new approach for supervised classification to handle mixed-data (i.e., categorical, binary, and continuous) data structures using a hybrid radial basis function neural networks (HRBF-NN). HRBF-NN supervised classification combines regression trees, ridge regression, and the genetic algorithm (GA) with radial basis function (RBF) neural networks (NN) along with information complexity (ICOMP) criterion as the fitness function to carry out both classification and subset selection of best predictors which discriminate between the classes. In this manner, we reduce the dimensionality of the data and at the same time improve classification accuracy of the fitted predictive model. We apply HRBFNN supervised classification to a real benchmark credit approval mixed-data set to classify the customers into good/bad classes for credit approval. Our results show the excellent performance of HRBF-NN method in supervised classification tasks.

AB - In this paper, we introduce a new approach for supervised classification to handle mixed-data (i.e., categorical, binary, and continuous) data structures using a hybrid radial basis function neural networks (HRBF-NN). HRBF-NN supervised classification combines regression trees, ridge regression, and the genetic algorithm (GA) with radial basis function (RBF) neural networks (NN) along with information complexity (ICOMP) criterion as the fitness function to carry out both classification and subset selection of best predictors which discriminate between the classes. In this manner, we reduce the dimensionality of the data and at the same time improve classification accuracy of the fitted predictive model. We apply HRBFNN supervised classification to a real benchmark credit approval mixed-data set to classify the customers into good/bad classes for credit approval. Our results show the excellent performance of HRBF-NN method in supervised classification tasks.

UR - http://www.scopus.com/inward/record.url?scp=84945551939&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945551939&partnerID=8YFLogxK

U2 - 10.1007/978-3-662-44983-7_2

DO - 10.1007/978-3-662-44983-7_2

M3 - Conference contribution

SN - 9783662449820

VL - 48

SP - 13

EP - 27

BT - Data Science, Learning by Latent Structures, and Knowledge Discovery

A2 - Bohmer, Matthias

A2 - Krolak-Schwerdt, Sabine

A2 - Lausen, Berthold

PB - Kluwer Academic Publishers

ER -