Recommendation System Designer
$2.99OfficialDesign recommendation systems: collaborative filtering, content-based, hybrid approaches, cold start, and ranking.
datarecommendationscollaborative-filteringrankingmlpersonalization· by SkillingMain
What you get
- ✓5-step procedure
- ✓4 pitfalls to avoid
- ✓Installs into 6 tools
- Version
- v1 →
- Last updated
- today
- Length
- 3 min read
- Requires
- Best with a strong model (Claude Sonnet 4)
Works in: Claude Code, Codex, Cline, opencode, OpenClaw, Hermes · Handles multi-file projects
Preview
When to use
Use when designing a recommendation engine for e-commerce, content platforms, media streaming, or B2B SaaS. Trigger on phrases like "recommendation system", "personalized feed", "you might also like", "relevant items". Do not use for simple rule-based sorting (most popular, newest) — this skill designs ML-driven personalization.
Inputs to gather
- Item catalog size and item metadata: products, articles, videos — and their attributes (category, tags, price, description)
- User interaction data: views, clicks, purchases, ratings, dwell time — and volume per day
- Cold start prevalence: what fraction of users are new? What fraction of items have no interaction history?
- Bu
…
🔒 Buy once ($2.99) to unlock the full playbook, download it, and install it in every tool you use.