Apache Solr Learning to Rank For The Win!

06/12/2017 - 11:00 to 11:40
Palais Atelier
long talk (40 min)

Session abstract: 

Learning to rank is a technique for automatically improving the quality of results produced by a search engine. It was initially proposed in academia around 17 years ago and almost all commercial web search engines  employ it in some form or other. At Bloomberg, we decided that it was time for an open source engine to support learning to rank, so we spent more than a year designing and implementing it. The results of our effort have been accepted by the community and our Learning to Rank plugin is now available in the latest release of Apache Solr (version 6.4). In this talk we will explain how learning to rank works, how we implemented and integrated it into Apache Solr, and how you can use it to improve the quality of the results in your search engine.