Recommendation System Designer

Name: OpenModels
Creator: OpenModels
License: https://github.com/openmodelsrun/openmodels

AvanzadadataContexto mínimo: 32K

Designs recommendation systems end to end: candidate generation, ranking, and re-ranking. Covers collaborative filtering, content-based and embedding retrieval, two-tower models, cold-start strategies, feature stores, offline/online evaluation (NDCG, recall@k), and feedback loops. Produces an architecture and evaluation plan tailored to the product.

recommendations machine-learning ranking embeddings personalization

Casos de uso

Designing a product recommendation pipeline
Choosing candidate generation and ranking approaches
Handling cold-start for new users and items
Defining offline and online evaluation metrics
Building a feedback loop from implicit signals

Prompt de ejemplo

Design a recommendation system for a marketplace with 2M items and 500K users.
Provide:
1. Candidate generation and ranking architecture
2. Feature and embedding strategy
3. Cold-start handling for new users/items
4. Offline metrics (recall@k, NDCG) and an online A/B plan
5. A feedback loop from clicks and purchases

Modelos recomendados

claude-opus-4-7 gpt-5-5-pro gemini-3-1-pro deepseek-v4

Herramientas compatibles

claude-codekiroany

Modalidades

Entrada: text

→

Salida: text, code

Skills relacionadas

feature-engineering-assistant rag-pipeline-builder ab-test-setup

Autor

OpenModels Community

@openmodelsrun