A data mining based inverse classification with hybrid genetic approaches

Mu-Chen Chen*, Chia Ping Lin, Shih Hsien Huang, Wei Rong Zeng

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

Abstract

The credit scoring models are developed to categorize applicants as either accept or reject with respect to their characteristics, and thereby to minimize the creditors' risk and translate considerably into future savings. In this paper, we use Genetic Programming (GP) as a classification system to build the credit scoring model. The post classification analysis, namely inverse classification, is adopted to better understand rejected credits, and try to reassign them to the accept class. An optimization method based on genetic algorithm (GA) is used to reassign the rejected instances to the accept class for balancing between adjustment cost and customer preference.

Original languageEnglish
Pages1668-1675
Number of pages8
StatePublished - 1 Dec 2006
Event36th International Conference on Computers and Industrial Engineering, ICC and IE 2006 - Taipei, Taiwan
Duration: 20 Jun 200623 Jun 2006

Conference

Conference36th International Conference on Computers and Industrial Engineering, ICC and IE 2006
CountryTaiwan
CityTaipei
Period20/06/0623/06/06

Keywords

  • Credit scoring
  • Genetic algorithm
  • Genetic programming
  • Inverse classification

Fingerprint Dive into the research topics of 'A data mining based inverse classification with hybrid genetic approaches'. Together they form a unique fingerprint.

Cite this