Conferences News

Haystack Live!

Haystack is the conference for organizations where search, matching, and relevance really matters to the bottom line. For search managers, developers, relevance engineers & data scientists finding ways to innovate, see past the silver bullets, and share what actually has worked well for their unique problems

Location: online

Date: 24th March 2022

// our talk

Online Testing Learning to Rank with Solr Interleaving

Learning to Rank (LTR) is the application of machine learning in the training of ranking models for search systems. It has been contributed to Apache Solr in version 6.4.0 back in 2017. Organizations struggle with the problem of how to test online different models to identify the best for their users. Interleaving is an online evaluation approach that compares ranking functions by mixing their results and interpreting the users’ implicit feedback(such as clicks). This talk describes the contribution of the Interleaving capability to the Learning To Rank module in Apache Solr (from 8.8.0) and explains how to use it. You will learn:

  • how Interleaving approaches work, with a focus on Team-Draft Interleaving
  • how the Apache Solr implementation works
  • how to use it to compare ranking models and also the original score
  • how to collect and evaluate users’ interactions with the interleaved list to identify the best performing model

Join us as we explore this new Apache Solr feature!

// our speaker

Alessandro Benedetti

Founder @ Sease
APACHE LUCENE/SOLR COMMITTER
// video

Author

Lisa Biella

Lisa Biella is a creative digital marketer, geek at heart who is enthusiastic about technology and how it affects people’s lives.

Leave a comment

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.