Application of bayesian additive regression trees in the development of credit scoring models in Brazil
AUTOR(ES)
Brito Filho, Daniel Alves de, Artes, Rinaldo
FONTE
Prod.
DATA DE PUBLICAÇÃO
02/07/2018
RESUMO
Abstract Paper aims This paper presents a comparison of the performances of the Bayesian additive regression trees (BART), Random Forest (RF) and the logistic regression model (LRM) for the development of credit scoring models. Originality It is not usual the use of BART methodology for the analysis of credit scoring data. The database was provided by Serasa-Experian with information regarding direct retail consumer credit operations. The use of credit bureau variables is not usual in academic papers. Research method Several models were adjusted and their performances were compared by using regular methods. Main findings The analysis confirms the superiority of the BART model over the LRM for the analyzed data. RF was superior to LRM only for the balanced sample. The best-adjusted BART model was superior to RF. Implications for theory and practice The paper suggests that the use of BART or RF may bring better results for credit scoring modelling.
Documentos Relacionados
- Construção de modelos credit scoring com análise discriminante e regressão logística para a gestão do risco de inadimplênciaa de uma intituição de microcrédito.
- Estimating credit and profit scoring of a Brazilian credit union with logistic regression and machine-learning techniques
- Modelagem de risco de crÃdito: aplicaÃÃo de modelos Credit Scoring no Fundo Rotativo de AÃÃo da Cidadania â Cred Cidadania
- Psicologia do risco de crédito: análise da contribuição de variáveis psicológicas em modelos de credit scoring
- Bayesian binary regression model: an application to in-hospital death after AMI prediction