Meu SciELO
Serviços Personalizados
Artigo
Indicadores
- Citado por SciELO
Links relacionados
- Similares em SciELO
Compartilhar
Revista Cubana de Ciencias Informáticas
versão On-line ISSN 2227-1899
Resumo
LOPEZ RODRIGUEZ, Yoan Antonio; HIDALGO DELGADO, Yusniel e SILEGA MARTINEZ, Nemury. Method for the integration of ontologies in a credit scoring system. Rev cuba cienc informat [online]. 2016, vol.10, n.4, pp. 97-111. ISSN 2227-1899.
ABSTRACT The banks are financial institutions that evaluate the credit risk to customers. The information systems for the credit evaluation support the risk analysts in this evaluation process. In the reviewed literature, we found that there are systems for the evaluation of credits based on Artificial Intelligence techniques, including the ontologies as form of knowledge representation. In this sense, we did not find evidence about credit scoring systems using both, ontological and relational model together. In this paper, we propose a novel method for integrating ontologies in credit scoring systems based on relational databases. The method is based on seven activities that they include: to develop the relational model, to develop the ontological model, to load the ontological model, to populate the ontological model, to infer knowledge, to offer the outputs and to validate the solution. To evaluate the applicability of the proposed method, it was used in the implementation of one system for the evaluation of credits based on ontologies in the National Bank of Cuba. We used Protégé 5.0 as development tool of ontologies and the methodology for the development of ontologies proposed by Rubén Darío Alvarado. In order to the load and manipulation of ontologies were used the framework Jena and OWL API. With the use of the proposed method was obtained a system reusable, flexible and easy to maintain.
Palavras-chave : credit scoring; method; ontologies; Protégé.