• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.45.2000.tde-20210729-122749
Document
Author
Full name
Paulo de Tarso Marques Rosa
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2000
Supervisor
Title in Portuguese
Modelos de 'credit scoring': regressão logística, 'chaid' e real
Keywords in Portuguese
Estatística Aplicada
Abstract in Portuguese
O mercado financeiro de varejo brasileiro encontra-se em um momento de expansão da concessão de crédito, ocasionando um forte aumento na demanda por ferramentas capazes de avaliar o risco de inadimplência dos potenciais contratantes de produtos de crédito. Modelos estatísticos, denominados modelos de 'Credit Scoring', estão sendo utilizados para esta finalidade. Neste trabalho, descrevemos as caracteristicas dos processo de concessão de crédito e a partir de uma amostra de dados, fornecida por uma instituição financeira brasileira, aplicamos e comparamos três técnicas para classificação de clientes: a Regressão Logística Múltipla, o CHAID e o REAL. As duas primeiras técnicas são bastante utilizadas por profissionais do mercado e a terceira, trata-se de um novo algoritmo de Árvore de Classificação, sendo a primeira vez que é aplicado ao problema. Vantagens e desvantagens de cada um dos métodos são apresentadas
Title in English
not available
Abstract in English
Cosumer credit is an extremely significant factor in Brazilian economic expansion. Financial institutions are looking for efficient tools to evaluate the risk of consumer loans. Some statistical Credit Scoring Models have already been used for this evaluation. In this study we apply three methods in a sample set of applicants from a Brazilian Bank. Two of these methods, Multiple Logistic Regression and CAID, are well known and have good reputation in the financial community. The third method, the REAL, is a new decision tree algorithm and was adapted to be as a credit scoring technique. We compare the performance of these three methods to the data. We discuss the avanteges and disadvantages of each method
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2021-07-29
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.