Bibliographic citations
Cáceres, A., Paucar, F. (2020). Modelo de Data Science para la evaluación de clientes de cajas rurales sin historial crediticio [Tesis, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/653294
Cáceres, A., Paucar, F. Modelo de Data Science para la evaluación de clientes de cajas rurales sin historial crediticio [Tesis]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2020. http://hdl.handle.net/10757/653294
@misc{renati/392127,
title = "Modelo de Data Science para la evaluación de clientes de cajas rurales sin historial crediticio",
author = "Paucar Villantoy, Fabio Leonel",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2020"
}
In Latin America, financial inclusion has increased considerably in recent years, but it still does not cover the entire workforce. According to World Bank studies, access to credit in Latin America represents only 51% and in Peru this figure drops to 29%. In the financial sector, the requirements for applying for credit are very rigid, giving priority to the formal sector. According to the International Labor Organization, 69% of the labor force in Peru is informal. Furthermore, in this sector the loans granted are small amounts and lack credit history, making the costs and risk associated with such loans high for the entities. That is why the analysis in the evaluation of the client without credit history is deficient with the reality that they present. The development of this project responds to the fact that the great majority of financial entities grant credits to clients who already have some credit history, therefore, what we want to show, unlike the rest, is that a credit can also be granted to people or micro entrepreneurs who are not yet totally formalized or do not present proof of income (ballots or receipt for fees). There are precedents of this type of cases at international level, particularly in China that have another reality to ours, but some concepts can be transferred to our project. Based on the above, we propose the development of a Data Science model that will allow us to evaluate potential clients and, in turn, evaluate their ability to pay and offer them an associated product for each client. To this end, the model was tested on a web page within the entity on their computers and outside through the use of mobile devices, in order to show results obtained by the model indicating improvements in the percentage of credit granted to clients by officials. Keywords: data science, evaluation model, payment capacity, data analysis, credit history, rural saving bank.
This item is licensed under a Creative Commons License