Feature engineering for marketplace recommenders — what to extract from raw marketplace assets (listing photos, owner-entered listing metadata, sitter wizard responses) to power item-to-item (similar listings), user-to-item (homefeed ranking), or user-to-user (mutual-fit matching) recommenders. Covers asset auditing, first-principles feature decomposition, vision-feature extraction (CLIP, room-type, amenities, aesthetics), listing text and metadata encoding, sitter wizard design, derived-composition patterns for i2i / u2i / u2u (ANN shelves, two-tower, mutual-fit), feature quality governance (training-serving parity, drift, PII), and incremental value proof (ablation A/B, kill reviews, feature-free baseline). Trigger even when the user does not explicitly say "feature engineering" but is asking how to get more signal out of listing photos, listing metadata, or the sitter onboarding wizard, or how to improve i2i / u2i / u2u quality without blindly ingesting a new model.
Feature engineering for marketplace recommenders — what to extract from raw marketplace assets (listing photos, owner-entered listing metadata, sitter wizard responses) to power item-to-item (similar listings), user-to-item (homefeed ranking), or user-to-user (mutual-fit matching) recommenders. Covers asset auditing, first-principles feature decomposition, vision-feature extraction (CLIP, room-type, amenities, aesthetics), listing text and metadata encoding, sitter wizard design, derived-composition patterns for i2i / u2i / u2u (ANN shelves, two-tower, mutual-fit), feature quality governance (training-serving parity, drift, PII), and incremental value proof (ablation A/B, kill reviews, feature-free baseline). Trigger even when the user does not explicitly say "feature engineering" but is asking how to get more signal out of listing photos, listing metadata, or the sitter onboarding wizard, or how to improve i2i / u2i / u2u quality without blindly ingesting a new model.
Marketplace Engineering Recsys Feature Engineering Best Practices
Comprehensive first-principles guide for deriving usable recommender features from the raw assets of a two-sided trust marketplace — listing photos, owner-supplied listing metadata, and sitter wizard responses — for item-to-item, user-to-item, and user-to-user solutions. Contains 44 rules across 8 categories ordered by cascade impact on the feature-engineering lifecycle, plus one playbook that composes the rules into an end-to-end feature discovery workflow.
This skill is the upstream precursor to marketplace-personalisation (AWS Personalize) and marketplace-search-recsys-planning (OpenSearch retrieval). Those skills treat features as inputs they already have; this skill is about deciding what features to build from the raw assets, which decisions they serve, and how to prove each one is worth its maintenance cost.
When to Apply
Reference this skill when:
Planning what to extract from listing photos, descriptions, or amenity lists to power i2i similarity or u2i ranking
Designing or revising the sitter onboarding wizard with recsys features as the primary output
Deciding whether to build a vision embedding pipeline, a text encoder, or neither — and in what order
Composing existing base features into item-to-item, user-to-item, or user-to-user scoring
Auditing an existing feature store for coverage, drift, PII, duplication, or orphan features
Choosing a ship/kill criterion for a new recsys feature and designing the ablation A/B test
Answering the question: "we want to improve the similar-homes shelf — what feature should we build?"
Setup
This skill has no user-specific configuration — it is self-contained. References are live URLs to engineering blogs from Airbnb, Pinterest, DoorDash, Uber, Netflix, and Google, to open-source libraries (Feast, Sentence-Transformers, Hugging Face CLIP, H3), to foundational academic papers (Airbnb KDD 2018, Pinterest ItemSage, YouTube Semantic IDs, PinSage), and to Google's Rules of Machine Learning.
Rule Categories
Categories are ordered by cascade impact on the feature-engineering lifecycle: auditing mistakes build features on data that does not exist, first-principles mistakes produce features that do not map to real decisions, extraction mistakes poison everything downstream, and so on. Fix earlier-stage problems before later-stage problems.
One playbook composes the rules into an end-to-end workflow:
references/playbooks/discovering.md — Discover new features from raw marketplace assets: a seven-step workflow that starts with an asset audit and a decision decomposition and ends with a shipped ablation A/B against a feature-ablated baseline. Use when the task is "what should we build next?" rather than "fix this specific feature."
Read the playbook first when the task is an open-ended "how do we extract more signal from X?" Read individual rules when a specific implementation question arises.
marketplace-personalisation — Post-extraction personalisation on AWS Personalize: event tracking, schema design, two-sided matching, cold start, feedback loops. Hand off once your features are in the store and you are ready to train a ranker.
marketplace-search-recsys-planning — OpenSearch retrieval planning: query understanding, index design, ranking, search-plus-recs blending. Hand off when the bottleneck is retrieval rather than feature availability.
marketplace-pre-member-personalisation — Pre-member journey from anonymous visit to paid membership: anonymous signal inference, onboarding intent capture, pre-member measurement. Hand off at the paid-member boundary.
