Multi-Model Content Recommendation: An Ensemble Architecture
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Lingua: | inglese |
| Pubblicazione: |
Zenodo
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866902062302756864 |
|---|---|
| author | Joshi, Shweta |
| author_facet | Joshi, Shweta |
| contents | <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> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_20367553 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Multi-Model Content Recommendation: An Ensemble Architecture Joshi, Shweta recommendation systems ensemble methods LDA latent Dirichlet allocation collaborative filtering ALS LSH-MinHash locality-sensitive hashing multi-model orchestration candidate generation content recommendation <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> |
| title | Multi-Model Content Recommendation: An Ensemble Architecture |
| topic | recommendation systems ensemble methods LDA latent Dirichlet allocation collaborative filtering ALS LSH-MinHash locality-sensitive hashing multi-model orchestration candidate generation content recommendation |
| url | https://doi.org/10.5281/zenodo.20367553 |