https://www.infoq.com InfoQ OpenSearch News feed https://www.infoq.com/news/2026/05/swiggy-autocomplete-rt-ranking/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=OpenSearch-news <img src="https://res.infoq.com/news/2026/05/swiggy-autocomplete-rt-ranking/en/headerimage/header-1778975533066.jpg"/><p>Swiggy detailed real-time machine-learning ranking system for autocomplete built on OpenSearch. The architecture separates candidate generation and ranking, uses feature stores for real time signals, and applies learning to rank models for improved relevance. It replaces heuristic ranking while maintaining strict latency constraints and enabling continuous model updates from user behavior signals.</p> <i>By Leela Kumili</i> OpenSearch learning Low Latency Real Time Infrastructure Rankings Machine Learning Event Driven Architecture Search Development Architecture & Design news Mon, 18 May 2026 14:38:00 GMT https://www.infoq.com/news/2026/05/swiggy-autocomplete-rt-ranking/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=OpenSearch-news Leela Kumili 2026-05-18T14:38:00Z /news/2026/05/swiggy-autocomplete-rt-ranking/en