Recommendation System Designer
ПродвинутыйdataМинимальный контекст: 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.
Варианты использования
- 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
Пример промпта
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
Рекомендуемые модели
Совместимые инструменты
claude-codekiroany
Модальности
Вход: text
→Выход: text, code
Похожие Skills
Автор
OpenModels Community