Diseño de un modelo basado en redes neuronales en la nube para determinar el riesgo de crédito en los solicitantes de microcrédito en el mercado financiero de Perú

Published in: Innovation in Education and Inclusion : Proceedings of the 16th LACCEI International Multi-Conference for Engineering, Education and Technology
Date of Conference: July 18-20, 2018
Location of Conference: Lima, Perú
Authors: César Canelo (Universidad Nacional de Ingeniería, PE)
Paúl Tocto (Universidad Nacional de Ingeniería, PE)
Full Paper: #504

Abstract:

Credit institutions have always had the problem of controlling the credit risk they are exposed to when developing their credit operations, in that sense, they have always required to rely on predictive models that help them make the right decisions for the acceptance or rejection of a loan. credit application. They are the well-known classical models based on statistical techniques and models based on artificial intelligence techniques. These models differ in the number of factors they require, in the techniques they employ and in the accuracy of the prediction. In this study, it is proposed to apply a methodology based on neural networks, which will allow the model to learn and adjust according to the information provided by the client. Microsoft Azure Machine Learning Studio is used, new software available in the cloud, which evaluates various models based on neural networks to determine which model best fits the data and minimizes the prediction error.