Recommendation Systems (15): Real-Time Recommendation and Online Learning

Mon, 12 Jan 2026 09:00:00 +0000

A user opens your app at 14:02 and searches for ’trail running shoes’. By 15:30, they’ve moved on to reading kitchen reviews. A model that retrains nightly still shows them Salomon ads at 16:00 — and that gap is exactly the bug a real-time system fixes. The interesting part isn’t ‘make it faster’ but ‘what should be fast’ — most features add nothing to AUC even when made real-time, and the wrong design point wastes money without improving performance.

Online Learning on Chen Kai Blog

Recommendation Systems (15): Real-Time Recommendation and Online Learning