How Chalk fuels Whatnot’s live shopping platform

Whatnot is the largest live shopping platform in the U.S. and Europe, a marketplace where buyers and sellers connect through real-time, community-driven commerce. The company surpassed $3 billion in live sales last year alone, with users spending on average 80 minutes a day browsing and buying from live shows.

As with most e-commerce marketplaces, personalization is critical. The first few seconds a user opens the app determine whether they’ll find a show they care about and whether a seller makes a sale. Feed recommendations are central to that moment.

As Whatnot scaled, its ML systems started to lag behind product needs. The original batch-based architecture, which generated billions of user–show predictions nightly, struggled to keep up with fast-changing inventory, new seller launches, and real-time user behavior. Cold starts were common, coverage dropped, and model iteration slowed, all of which impacted the quality of the recommendations powering the core app experience.

The Data & AI team began rebuilding the recommendation system to support real-time online inference. They needed infrastructure that could serve tens of thousands of features per request at low latency, across deeply nested graphs and high-throughput workloads. They chose Chalk to power all core recommendation systems, from feed ranking to show discovery.

At Whatnot’s scale, we couldn’t deliver personalization without a real-time feature engine. Chalk is core infrastructure.

Emmanuel Fuentes VP, Data & AI at Whatnot

As a live e-commerce marketplace, Whatnot’s core ML task is matching buyers to sellers quickly and accurately.

Each user session triggers a model that scores thousands of livestreams, many added moments earlier, and determines what to rank first. For much of the company’s growth, ranking and recommendations were powered by an offline pipeline that generated over 10 billion predictions each night.

While effective at small scale, this architecture introduced sharp tradeoffs as traffic and seller volume grew:

• New sellers were delayed: cold starts required 24 hours before personalized content appeared in ranked feeds
• Session signals were dropped: the batch system couldn’t include recent behavior like taps or watches
• Coverage fell: as inference scale grew, prediction coverage dropped to ~90%
• Waste grew: trillions of scores were computed but never used
• Model velocity stalled: new versions were hard to test and deploy

All of this made it more challenging to iterate quickly, personalize effectively, and scale reliably.

We needed a system that could reflect what was happening on the platform right now—not 12 hours ago. Moving to real-time inference was the only way to keep pace with our users and sellers.

Faithful Alabi Software and Data Engineer, Whatnot

Whatnot adopted Chalk to power its real-time feature infrastructure, serving as both the company’s feature store and online feature engine. The goal was to unify training and inference, reduce operational complexity, and enable low-latency inference without sacrificing flexibility or scale.

Chalk serves as the system of record for features and as the real-time compute layer. Feature logic is defined once in code and reused across batch and online systems, reducing duplication and improving consistency. At inference time, Chalk materializes features from request context and historical data. Payloads exceed 1MB and include tens of thousands of features, yet the system consistently delivers responses under 150 milliseconds, even during peak traffic.

We’re moving hundreds of millions of features per second, each payload around 1MB, and still hitting a P99 latency of just 100ms. That kind of performance across the board is a real testament to the system Chalk built.

Emmanuel Fuentes VP, Data & AI at Whatnot

Chalk’s architecture allows Whatnot’s recommendation system to respond in real time to user behavior and marketplace activity, like browsing behavior, recent purchases, or seller activity. Because features are defined once and versioned in code, the team ships models faster and with more reliable deployment.

By combining feature storage with on-demand computation, Chalk has become a foundational part of Whatnot’s ML platform. It supports production workloads while enabling fast experimentation across teams.

Chalk gives us a single abstraction for online and offline features. That’s helped reduce bugs, speed up deployment, and made it easier to reason about feature correctness.

Jacob Burkett Senior Data Engineer, Whatnot

Here’s how Chalk fits into Whatnot’s real-time inference loop:

System performance at a glance:

• Supports 300M+ features/sec, including high-cardinality lookups and session-level joins
• Low latency under load, with optimized paths ~70ms and P99 <100ms
• >99.99% uptime
• Load tested to handle 9x future traffic
• Supports fresher, more powerful signals, including 1-hour lookbacks (moving toward 1-minute)

Whatnot uses Chalk resolvers to compute features from data warehouses, streams, and request inputs — all through a unified query plan. The same feature definitions are reused across batch training and online inference, helping the team maintain consistency and move faster.

With Chalk in place, Whatnot powers all feed recommendations using real-time online inference. The shift has driven measurable improvements across engineering efficiency and commercial performance:

Chalk worked with us on infrastructure tuning, latency tail issues, and scaling readiness. It isn’t just a tool — it feels like adding capability to our team.

Emmanuel Fuentes VP, Data & AI at Whatnot

What started with real-time feed ranking has steadily expanded. Today, Chalk supports a growing number of ML use cases across Whatnot’s business.

• All core recommendation systems rely on Chalk to compute and serve real-time features for feed ranking, and show suggestions.
• Fraud and trust models plan to leverage session-level and behavioral features, served in real time via Chalk without duplicating infrastructure.
• Experimentation workflows use Chalk to snapshot feature values at inference time, ensuring test consistency and accurate evaluation.

We’re constantly load testing to stay ahead of our own growth. Chalk has scaled with us from the early stages, and we’re confident it’ll support where we’re going.

Emmanuel Fuentes VP, Data & AI at Whatnot

Chalk plays a foundational role in Whatnot’s growth. It provides stability under peak load, but more importantly, its composable design allows Whatnot to scale up model complexity without scaling infrastructure burden. By unifying, computing, and serving features in one system, Chalk helps ensure machine learning stays a technical moat — powering a fast, personalized experience as the marketplace grows.

If you want to learn more about what Whatnot’s engineering team is up to, check out their blog.