Enhancing semantic consistency in anti-fraud rule-based expert systems

In this study, an ontology-driven approach is proposed for semantic conflict detection and classification inrule-based expert systems. It focuses on the critical case of anti-fraud rule repositories for the inspectionof Card Not Present (CNP) transactions in e-commerce environments. The main motivat...

Descripción completa

Detalles Bibliográficos
Autores: Roldán García, María del Mar, García Nieto, José Manuel, Aldana Montes, José F.
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2017
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/108686
Acceso en línea:https://hdl.handle.net/11441/108686
https://doi.org/10.1016/j.eswa.2017.08.036
Access Level:acceso abierto
Palabra clave:Semantic model
Ontology reasoning
Rule-based expert system
Fraud detection expert systems
Descripción
Sumario:In this study, an ontology-driven approach is proposed for semantic conflict detection and classification inrule-based expert systems. It focuses on the critical case of anti-fraud rule repositories for the inspectionof Card Not Present (CNP) transactions in e-commerce environments. The main motivation is to examineand curate anti-fraud rule datasets to avoid semantic conflicts that could lead the underpinning expertsystem to incorrectly perform, e. g., by accepting fraudulent transactions and/or by discarding harmlessones. The proposed approach is based on Web Ontology Language (OWL) and Semantic Web Rule Lan- guage (SWRL) technologies to develop an anti-fraud rule ontology and reasoning tasks, respectively. Thethree main contributions of this work are: first, the creation of a conceptual knowledge model for de- scribing anti-fraud rules and their relationships; second, the development of semantic rules as conflict- resolution methods for anti-fraud expert systems; third, experimental facts are gathered to evaluate andvalidate the proposed model. A real-world use case in the e-commerce (e-Tourism) industry is used toexplain the ontological knowledge design and its use. The experiments show that ontological approachescan effectively discover and classify conflicts in rule-based expert systems in the field of anti-fraud ap- plications. The proposal is also applicable to other domains where knowledge rule bases are involved.