SELECTING PROFILES OF IN DEBT CLIENTS OF A BRAZILIAN TELEPHONE COMPANY: NEW LASSO AND ADAPTIVE LASSO ALGORITHMS IN THE COX MODEL
AUTOR(ES)
Costa, Marcelo A., Colosimo, Enrico A., Miranda, Carolina G.
FONTE
Pesqui. Oper.
DATA DE PUBLICAÇÃO
2015-08
RESUMO
Variable selection plays an important rule in identifying possible factors that could predict the behavior of clients with respect to the bill payments. The Cox model is the standard approach for modeling the time until starting the lack of payments. Parsimony and capacity of predicting are some desirable characteristics of statistical models. This paper aims at proposing a new forward stagewise Lasso (least absolute shrinkage and selection operator) algorithm and applying it for variable selection in the Cox model. The algorithm can be easily extended to run the Adaptive Lasso (ALasso) approach.
Documentos Relacionados
- In new company: U1 snRNA associates with TAF15
- Innovative technology-based company: a development model for the Brazilian scenario.
- Absorptive Capacity in a Public Research Company: from Maturity to Scalability
- ORGANIZATIONAL CHANGE IN A BRAZILIAN FAMILIAR COMPANY: A CASE STUDY
- Brazilian Economy in the Eighties and the Debt Crisis