A new approach hybrid recommender system of item bundles for group of users

Bryam David Vega Moreno, Remigio Ismael Hurtado Ortiz, David Andres Morales Rivera

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución de conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

User recommendation is a big challenge for collaborative filtering, due to the large number of users a company can have today. In addition, the data to recommend products, entertainment programs, among others, have to be very dispersed, there are not many users sent a vote towards a product, generating a high spread to make a recommendation. To solve this problem, we propose a hybrid system, which uses collaborative filtering and content-based filtering techniques where we use the user's personal information (in this case the occupation or work) to segment them into groups and then use the rating of the items to be able to make predictions. We then make recommendations using aggregation techniques such as average, maximum and minimum, which will be evaluated with metrics such as RMSE and MAE in order to obtain the best recommendation approach. To carry out this hybrid recommendation system, we have used a public database called Movielens. The research aims to leave a baseline for future research so that the proposed system can be improved with different methods.

Idioma originalInglés
Título de la publicación alojada2019 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2019
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9781728128986
DOI
EstadoPublicada - nov 2019
Evento2019 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2019 - Ixtapa, Guerrero, México
Duración: 13 nov 201915 nov 2019

Serie de la publicación

Nombre2019 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2019

Conferencia

Conferencia2019 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2019
País/TerritorioMéxico
CiudadIxtapa, Guerrero
Período13/11/1915/11/19

Huella

Profundice en los temas de investigación de 'A new approach hybrid recommender system of item bundles for group of users'. En conjunto forman una huella única.

Citar esto