A fuzzy markov model for consumer credit behavior dynamics

Ke Liu*, Kin Keung Lai, Sy Ming Guu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

A heterogeneous fuzzy Markov model is built for modeling and forecasting credit behavior dynamics of credit card users in this paper. This model brings together a fuzzy rule-based inference system and the Markov chain. The credit migration rate matrix of the fuzzy Markov chain is obtained by the inference system based on reasonable setting of rules for each consumer, and updated at each time interval, a process which results in heterogeneity across consumers and over time, thereby imparting more flexibility and accuracy to the model to reflect the reality. Credit status evolution process is predicted for a simulated dataset of consumer credit behaviors.

Original languageEnglish
Title of host publicationProceedings of the 2009 International Joint Conference on Computational Sciences and Optimization, CSO 2009
Pages460-462
Number of pages3
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 International Joint Conference on Computational Sciences and Optimization, CSO 2009 - Sanya, Hainan, China
Duration: 24 04 200926 04 2009

Publication series

NameProceedings of the 2009 International Joint Conference on Computational Sciences and Optimization, CSO 2009
Volume1

Conference

Conference2009 International Joint Conference on Computational Sciences and Optimization, CSO 2009
Country/TerritoryChina
CitySanya, Hainan
Period24/04/0926/04/09

Fingerprint

Dive into the research topics of 'A fuzzy markov model for consumer credit behavior dynamics'. Together they form a unique fingerprint.

Cite this