Zepto’s Dual‑Sequence Ranker Merges History and Session Data for Millisecond‑Scale Personalisation
Zepto introduced a dual‑sequence re‑ranker that encodes a shopper’s long‑term purchase history and their in‑session actions with separate transformer encoders. A cross‑attention fusion layer merges the two streams, delivering personalized rankings in under 50 ms for millions of daily users. This architecture lets the app instantly shift recommendations between routine repurchases and context‑driven cross‑sells, boosting conversion rates.