Recommendations
ML based ranking using Nrtsearch
Our short summary of Yelp’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on engineeringblog.yelp.com (opens in a new tab)Problem
Search relevance suffered because traditional term‑based scoring couldn't use rich signals or learn feature weights.
Solution
They added an Inference Plugin to Nrtsearch that runs ML models like XGBoost inside the search engine, extracting features from documents and re‑ranking results on‑the‑fly.
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on engineeringblog.yelp.com (opens in a new tab)