CEBRA: A CasE-Based Reasoning Application to recommend banking products
[EN] Following data ethics and respecting the clients’ privacy, the banking environment can use the client data that is available to them to offer personalized services to its clients. Intelligent recommender systems can support this attempt through specialized technological architectures. This arti...
| Autores: | , , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión enviada para evaluación y publicación |
| Fecha de publicación: | 2021 |
| País: | España |
| Recursos: | Universidad de Salamanca (USAL) |
| Repositorio: | GREDOS. Repositorio Institucional de la Universidad de Salamanca |
| OAI Identifier: | oai:gredos.usal.es:10366/166762 |
| Acesso em linha: | http://hdl.handle.net/10366/166762 |
| Access Level: | acceso abierto |
| Palavra-chave: | Case-based reasoning Fog Computing Virtual agents Artificial intelligence Fintech Commercial banking |
| Resumo: | [EN] Following data ethics and respecting the clients’ privacy, the banking environment can use the client data that is available to them to offer personalized services to its clients. Intelligent recommender systems can support this attempt through specialized technological architectures. This article proposes the inclusion of CEBRA (CasE-Based Reasoning Application), a case-based reasoning system oriented to commercial banking, in a Fog Computing architecture coordinated by virtual agents. Throughout this article, the model of this architecture is presented and its life cycle is described, and improvements are proposed through the incorporation of several techniques in the retrieve and reuse phases, including the extraction of interests expressed by users on their social network profiles and collaborative filtering systems. A comprehensive case study has been carried out and a dataset of 60,000 cases has been generated to evaluate CEBRA. As a result, the Recommender System is presented, by including, the recommendation algorithm and a REST interface for its use. The recommendations are based on the user’s profile, previous ratings and/or additional knowledge such as the user’s contextual information. The proposal takes advantage of contextual information to support the promotion of banking and financial products, improving user satisfaction. |
|---|