Sequen CEO Zoe Weil: Ranking Models Should Optimize Purchases, Not Clicks
TWIML AI Podcast · rss · 2026-10-15
TWIML AI Podcast #780 features Sequen co-founder and CEO Zoe Weil on how e-commerce ranking systems can use live behavioral signals to optimize for purchases rather than clicks or search relevance.
Key points:
- Approaches built at data-rich social platforms don't translate well to retail; Sequen infers shopper intent from in-session interactions like scroll speed and hover duration, without relying on user identity.
- Architecture: "large event models" plus specialized models that turn streaming events into features for downstream rankers.
- Engineering: infrastructure for millisecond-level dynamic rankings, why the team chose Rust for the backend, and evaluation harnesses that tie model improvements to business outcomes.
- Also covers the tradeoffs between advertising and organic revenue, continuous model improvement, and the boundary between personalization and surveillance.
More from Apps
- AI agents for KFC franchises: owner estimates 3-5% more EBITDA — IgorCarron · 2026-10-15
- Blob0 launches: a macOS file-manager-style desktop client for S3 and Cloudflare R2 — yihui_indie · 2026-10-15
- Starlink in-flight WiFi so good it makes a 7-year Delta Diamond member consider switching to United — MatthewChang · 2026-10-15
- One-shot prompt turns a puzzle photo into a step-by-step guide site (and a cool favicon) — fofrAI · 2026-10-15
- Odessia launches licensed AI travel concierge that books hotels at agency rates with perks — rohanpaul_ai · 2026-10-15
- Having agents operate everyday apps may be a false premise, argues viral Chinese thread — sujingshen · 2026-10-15