An Interactive Personalized Recommender System / Selmani ,saadeddine  

Public ISBD Titre : An Interactive Personalized Recommender System Type de document : texte imprimé Auteurs : Selmani ,saadeddine, Auteur ; Drif,Ahlem, Directeur de thèse Editeur : Setif:UFA Année de publication : 2021 Importance : 1 vol (61 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems Neural Recommender Models Index. décimale : 004 - Informatique Résumé : Recommender systems are broadly used to suggest goods (e.g., products, news, ser- vices) that best match users' needs and preferences. The main challenge comes from modeling the dependence between the various entities incorporating multifaceted infor- mation such as user preferences, item attributes, and users' mutual in uence, resulting in more complex features. To deal with this issue, we design a recommender system incorporating a collaborative ltering (CF) module and a stacking recommender mod- ule. We introduce an interactive attention mechanism to model the mutual in uence relationship between aspect users and items. It allows mapping the original data to higher-order feature interactions. Additionally, the stacked recommender, composed of a set of regression models and a meta-learner, optimizes the weak learners' performance with a strong learner. The developed stacking recommender considers the content for recommendation to create a prole model for each user. Experiments on real-world datasets demonstrate that the proposed algorithm can achieve more accurate predic- tions and higher recommendation eciency. Côte titre : MAI/0520 En ligne : https://drive.google.com/file/d/1ZtxAepeudcr-piHs7plgVHPWSd11C16a/view?usp=shari [...] Format de la ressource électronique : pdf An Interactive Personalized Recommender System [texte imprimé] / Selmani ,saadeddine, Auteur ; Drif,Ahlem, Directeur de thèse . - [S.l.] : Setif:UFA, 2021 . - 1 vol (61 f .) ; 29 cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Recommender systems Neural Recommender Models Index. décimale : 004 - Informatique Résumé : Recommender systems are broadly used to suggest goods (e.g., products, news, ser- vices) that best match users' needs and preferences. The main challenge comes from modeling the dependence between the various entities incorporating multifaceted infor- mation such as user preferences, item attributes, and users' mutual in uence, resulting in more complex features. To deal with this issue, we design a recommender system incorporating a collaborative ltering (CF) module and a stacking recommender mod- ule. We introduce an interactive attention mechanism to model the mutual in uence relationship between aspect users and items. It allows mapping the original data to higher-order feature interactions. Additionally, the stacked recommender, composed of a set of regression models and a meta-learner, optimizes the weak learners' performance with a strong learner. The developed stacking recommender considers the content for recommendation to create a prole model for each user. Experiments on real-world datasets demonstrate that the proposed algorithm can achieve more accurate predic- tions and higher recommendation eciency. Côte titre : MAI/0520 En ligne : https://drive.google.com/file/d/1ZtxAepeudcr-piHs7plgVHPWSd11C16a/view?usp=shari [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0520	MAI/0520	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)