Recomendações de pizza em grupo: uma abordagem para aprimorar a experiência do usuário e as vendas em refeições coletivas
In a globalized context, permeated by an overload of online information, users face considerable challenges when exploring the vast array of available options. The complexity of this scenario results in less efficient and often frustrating consumption experiences. In light of this panorama, personal...
| Autores: | , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2024 |
| País: | Brasil |
| Institución: | Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) |
| Repositorio: | Repositório Institucional PUCRS |
| Idioma: | portugués |
| OAI Identifier: | oai:meriva.pucrs.br:10923/26798 |
| Acceso en línea: | https://hdl.handle.net/10923/26798 |
| Access Level: | acceso abierto |
| Palabra clave: | SISTEMAS DE RECOMENDAÇÃO SISTEMAS DE RECOMENDAÇÃO EM GRUPO FILTRAGEM COLABORATIVA FILTRAGEM BASEADA EM CONTEÚDO AGREGAÇÃO DE PREFERÊNCIAS ALIMENTAÇÃO RECOMMENDER SYSTEMS GROUP RECOMMENDER SYSTEMS COLLABORATIVE FILTERING CONTENT-BASED FILTERING PREFERENCE AGREGGATION FOOD CONSUMPTION |
| Sumario: | In a globalized context, permeated by an overload of online information, users face considerable challenges when exploring the vast array of available options. The complexity of this scenario results in less efficient and often frustrating consumption experiences. In light of this panorama, personalization and attractive offers emerge as crucial elements to enhance the connection between users and items, aiming to improve the consumer experience. Entrepreneurs, aware of this growing demand, seek systems capable of providing personalized recommendations, boosting both sales and user satisfaction. This work focuses on the challenging dynamics of recommendations in collective activities, with a focus on pizza suggestions. We present an innovative system that proposes an ideal collective dish, considering the individual preferences of all participants. This innovative approach uses a hybrid recommendation model, incorporating both collaborative filtering through the matrix factorization method with latent values, and content-based filtering through a clustering algorithm. The combination of these techniques, through preference aggregation, aims to create the perfect pizza, promoting a unique and satisfying culinary experience for all participants. |
|---|