Evolution of Yelp search to a generalized ranking platform

Umesh Dangat • Location: Theater 5 • Back to Haystack 2019

Elasticsearch forms the backbone of Yelp's core search.

The Learning to Rank elasticsearch plugin is one of the key tools that has transformed the Yelp Search team from serving linear ranking models only on the search page to powering a business ranking platform that serves all business recommendation applications across Yelp.

This talk will detail how Yelp's search engineers enhanced LTR plugin such that it would not only solve Yelp's current search needs but also enable future ranking use cases at Yelp.

Umesh Dangat

Yelp

I have 15 years of industry experience as a software developer most of it building distributed infrastructure to store and search data in realtime.

I lead the core search team at Yelp. During this time I have been instrumental in modernizing Yelp’s search infrastructure and moved it from a custom distributed lucene based ranking application to a generalized ranking application built on top of elasticsearch. I wrote a custom geocoder for Yelp to help mitigate reliance on third party geocoders. This systems now serves majority of the geocoding traffic at Yelp.

Lately I have been working on building a ranking platform at Yelp which enables multiple teams at Yelp to quickly deploy their machine learned models on elasticsearch for customized scoring.

I am an open source contributor for elasticsearch and a collaborator on the learning to rank plugin for elasticsearch.