Aplicação do Modelo Multi-estado de Markov em Cartões de Crédito / Application of the multi-state Markov model in credit cards

AUTOR(ES)

Daniel Evangelista Régis

DATA DE PUBLICAÇÃO

2007

RESUMO

Multi-state Markov models are used in the medical area so as to estimate transition probabilities between, for instance, various states of a disease, in which the patient can recover or die. The main interest of this work is to analyse the application of the Multi-state Markov model in the risk area associated to the use of credit cards, by means of investigating the characteristics of different state transitions of the relationship between clients and institutions throughout time and, therefore, generating score models for diverse purposes. Logistic regression models are also estimated in order to compare its results with the ones obtained by the Multi-state Markov model

ASSUNTO(S)

behaviour scoring logistic regression multi-state markov model economia cartões de crédito anti-attrition scoring regressão logística credit cards modelo multi-estado de markov anti-attrition scoring behaviour scoring

Documentos Relacionados

• Using multi-state markov models to identify credit card risk
• Projeção de domicílios por modelo multi-estado e aplicação para previsão da frota de automóveis em Belo Horizonte
• Aplicação do modelo ZAIG (Zero Adjusted Inverse Gaussian) na análise de uma carteira de cartões de crédito
• Analytical description of the activation of multi-state receptors by continuous neurotransmitter signals at brain synapses.
• Metodologia de identificação de vulnerabilidades em aplicações de pagamento utilizando cartões de crédito