Modelos de regressão defeituosos zero ajustados aplicados a dados de risco de crédito

Abstract

With the increase in consumption of goods, services, and credit granting, it becomes necessary to control the risk of the process. This measure aims to prevent a possible default rate higher than what financial institutions can bear and, at the same time, allows for profit generation. Several statistical techniques can be used to build models that provide an overview of the risk, and one of them is survival analysis. The application of this technique in the financial market seeks to study, for example, the time an individual takes to recover credit after the end of a financial crisis in their country. The use of such data can support the prediction of the ideal credit amount to be provisioned in possible crisis scenarios and infer when credit operations are likely to resume. In this context, this work aims to study two defective regression models for adjusted zero survival data modeling in the credit risk scenario. This approach allows for the accommodation of three types of units, such as customers with 'zero' survival times, i.e., early failures, customers susceptible and not susceptible to the event of interest. The methodology studied will be applied to a database provided by a leading institution in credit services and information in Brazil.