Table des matières: :: Library Catalog

Enregistré dans:

Détails bibliographiques
Auteur principal:	Joshi, Shweta
Format:	Recurso digital
Langue:	anglais
Publié:	Zenodo 2026
Sujets:	recommendation systems ensemble methods LDA latent Dirichlet allocation collaborative filtering ALS LSH-MinHash locality-sensitive hashing multi-model orchestration candidate generation content recommendation
Accès en ligne:	https://doi.org/10.5281/zenodo.20367553
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Table des matières:

<p>This paper describes a multi-model recommendation ensemble developed for CNET that combines four fundamentally different recommendation paradigms — topic modeling (LDA), user-user collaborative filtering (ALS), item-item collaborative filtering, and locality-sensitive hashing (LSH-MinHash) — under a meta-orchestration layer. Each model contributes a distinct recommendation signal: semantic content similarity, user behavior similarity, item co-consumption patterns, and efficient set-based similarity. The paper documents the architecture, the individual model designs, the orchestration strategy, and discusses the ensemble approach in the context of modern recommendation systems.</p>

Documents similaires