En el país, sobre todo en la ciudad de Chiclayo, las entidades bancarias realizan diversas transacciones que benefician a la población, una de ellas es el préstamo. Estas entidades, especificando el Banco Azteca, ha realizado diversos préstamos beneficiando a la población ya sea con negocios, empresas y otras deudas previa evaluación. Sin embargo, así como hay personas que cumplen en devolver el dinero prestado, existen otras personas que no lo realizan quedándose con el dinero por diversos factores ocasionando que estos automáticamente pasen al Sistema de Deudores. Este factor, en varias oportunidades no se ha tomado en cuenta, generando deudas en el Banco. Ante la mencionada situación, la presente tesis tuvo como objetivo general implementar una aplicación móvil utilizando el algoritmo de redes neuronales para la detección de clientes en las listas priorizadas en el Sistema del Banco Azteca identificando las listas de alto riesgo y validando el sistema de detección según la ISO 25010 teniendo en cuenta que el modelo se detectará en base a los datos obtenidos y según su historial generando un nivel de información registrada de los clientes. Los resultados obtenidos permitirán detectar con mayor precisión la morosidad de los clientes. Además, los empleados de la entidad podrán monitorear a sus clientes y realizar una simulación para determinar si el cliente puede llegar a ser moroso a futuro. / In the country, especially in the city of Chiclayo, banking entities carry out various transactions that benefit the population, one of them is the loan. These entities, specifying Banco Azteca, have made various loans benefiting the population either with businesses, companies and other debts after evaluation. However, just as there are people who comply with repaying the borrowed money, there are other people who do not do so, keeping the money for various factors, causing them to automatically go to the Debtors System. This factor, on several occasions, has not been taken into account, generating debts in the Bank. Given the aforementioned situation, the present thesis had the general objective of implementing a mobile application using the neural network algorithm for the detection of clients in the prioritized lists in the Banco Azteca System, identifying high-risk lists and validating the detection system according to ISO 25010, taking into account that the model will be detected based on the data obtained and according to its history, generating a level of registered information from the clients. The results obtained will make it possible to more accurately detect customer delinquency. In addition, the entity's employees will be able to monitor their clients and carry out a simulation to determine if the client may become delinquent in the future.

Made available in DSpace on 2010-04-20T21:00:09Z (GMT). No. of bitstreams: 4 Roberta Cardim Geyer.pdf.jpg: 50109 bytes, checksum: 17360d1565984b98377af09e99259b17 (MD5) Roberta Cardim Geyer.pdf.txt: 39031 bytes, checksum: 1c5647e853c916a21de4977887b19b5d (MD5) Roberta Cardim Geyer.pdf: 121342 bytes, checksum: 4713b946e4198241bc90a44fcd409ff0 (MD5) license.txt: 4886 bytes, checksum: 94d66dc6376195a94715754a4815db07 (MD5) Previous issue date: 2009-02-09T00:00:00Z / The main aim of this paper is to examine which factors are determinants of the mortgage debt system depth. Using data on legal creditor rights, credit information systems, constraints on executive and macroeconomic stability in 93 countries from 1996 to 2007, I found that countries with strong legal rights for borrowers and lenders, deeper credit information systems and more stable macroeconomic environment have deeper mortgage debt system. / O objetivo deste trabalho é analisar os fatores que determinam o desenvolvimento do crédito imobiliário nos países. Com dados de crédito imobiliário de 93 países de 1996 a 2007, estudo em que medida um ambiente macroeconômico estável, fortes direitos legais (através de leis de falência), sistemas de informação de crédito mais profundos e restrições ao poder do executivo influenciam a expansão do crédito imobiliário. Analisando países desenvolvidos e em desenvolvimento, controlando pelo tamanho do país, concluí que países com baixa volatilidade da inflação e do crescimento do PIB, com leis de qualidade e alta restrição ao poder executivo têm crédito habitacional mais desenvolvido.