Power recommender systems with real-time features
Chalk powers personalized feeds by computing fresh user, item, and marketplace features at request time. Teams use Chalk to serve recommendations that reflect real-time behavior and semantic similarity across dynamic inventories.
TALK TO AN ENGINEER
Trusted by leading teams building real-time personalization
Why Chalk for recommendation systems and personalization
Compute recommendation features in single-digit milliseconds
Define embeddings, affinity scores, and session features, and compute them at request time.
Serve live behavioral features
Use clicks, views, searches, and interactions as real-time inputs to feed ranking and personalization.
Keep training and serving consistent
Reuse the same feature definitions between training and inference to avoid inconsistencies in feeds.
Compute recommendation features in single-digit milliseconds
Define embeddings, affinity scores, and session features, and compute them at request time.
Serve live behavioral features
Use clicks, views, searches, and interactions as real-time inputs to feed ranking and personalization.
Keep training and serving consistent
Reuse the same feature definitions between training and inference to avoid inconsistencies in feeds.
Scale personalization consistently
Serve millions of personalized experiences per second with predictable low latency as candidate sets grow and inventory changes rapidly.
Deliver more relevant feeds
Personalize content and products using live user context instead of static profiles.
Handle cold starts in marketplaces
Surface relevant items and sellers for new users and inventory using embeddings and request-time features.
Live auction recommendations at scale
Live auction recommendations at scale
Whatnot delivers dynamic recommendations during live streams with Chalk, serving user and product features instantly to maximize engagement.
Personalize product and
content feeds in real time.
Compute user, item, and session features at request time to rank products based on live behavior and semantic similarity.
Personalize offers and experiences
using live account signals.
Compute fresh user and account features at request time to personalize product feeds and recommendations across changing financial context.
Adapt discovery as inventory
and preferences change.
Compute relevance and availability features at query time so listings reflect live inventory, location context, and evolving user intent.
Personalize recommendations
using live context and embeddings.
Use embeddings and request-time features to surface relevant content or care pathways based on recent activity and contextual signals, while reusing the same feature definitions for evaluation and production.
Embedding-based discovery
Match users to items or sellers using semantic similarity.
Chalk computes embeddings and retrieves candidates via vector search, then personalizes results using real-time context, supporting large candidate sets without relying on static precomputed recommendations.
Built for dynamic marketplaces
Built for dynamic marketplaces
Marketplaces introduce additional complexity. Inventory turns over rapidly. Buyers, sellers, and items constantly cold start. Signals are spread across multiple entities.
Chalk models these relationships explicitly and computes features across them at request time, allowing personalization to adapt instantly as users interact, inventory changes, or new items are introduced.
Query PlannerDesigning a feature platform that fits all team use cases, and still performs, was one of our biggest challenges.
Meng Xin Loh Technical Product Manager
More Resources
Build feeds that respond
in real time
Use Chalk to compute recommendation features when relevance matters most.
TALK TO AN ENGINEER
