In this two day training course delivered by Doug Turnbull and Elizabeth Haubert we go hands on with machine learning tools to improve relevance. Using an open source search engine, we see our models come to life, see the pitfalls of letting machines control relevance, and work to mitigate those pitfalls. From Hello World to Learning to Rank Lessons you can avoid learning the hard way. See how you can apply open source tooling to optimize your search results with machine learning. Ideal for production focused data scientists, relevance engineers, machine learning engineers, or search developers. Some familiarity with a search engine is expected.
Day One: Hands on Basics
We get hands on with a corpus and training data. We use Solr or Elasticsearch Learning to Rank plugin, hypothesize what features improve relevance, train and analyze models.
- Search Relevance as an Machine Learning Problem
- Cutting your Teeth With Your First Model
- Using Solr / Elasticsearch Learning to Rank Plugins
- What’s Wrong with My Judgments?
- Iterating on Features
- Choosing the Best Learning to Rank Model
- Model Verification, Checks, and Balances
Day Two: Real-World Learning to Rank
Using Learning to Rank hands-on. We use what you learned in day one to experiment with a larger training set. We also cover how to arrive at high-quality training data from user clicks and conversions
- Hacking on real Learning to Rank exercises using your knowledge from Day One
- Generating high quality training data using clicks & conversions
- Dealing with Presentation Bias
- Including Non-User Relevance Concerns (Business Rules and Marketplace concerns)
- The Next Frontiers of ML and Search
What You’ll Get Out Of It
- Using Solr or Elasticsearch Learning to Rank Plugins
- Building, analyzing, and improving Learning to Rank Models
- Choosing the best Learning to Rank Features
- Dealing with classic Machine Learning + Search Pitfalls
- Hands-on, using Machine Learning to improve search, using Jupyter notebooks
- How to measure search quality using analytics, conversions, and clicks
Your Trainers: Experienced Learning to Rank Experts
Doug Turnbull and Elizabeth Haubert have worked on Learning to Rank projects for a number of OpenSource Clients including Snag, Wikipedia, and others. Elizabeth Haubert has a Masters degree focused on Information Retrieval. Doug Turnbull wrote the book “Relevant Search” and was part of the team that created the Elasticsearch Learning to Rank plugin.
Style of Training: Small Group Workshop
Our trainers are not ‘stock tech trainer’ from central casting mindlessly reading slides. Our trainers expect to problem solve and think about your tough problems in real-time. As OpenSource Connection’s mission is to ‘empower search teams’, we see training as the central component to our mission. Our training is ‘workshop style’ where much of the value is the interactions and knowledge sharing between the small class and the two trainers.
Who This Training is For
We expect some familiarity with using Solr or Elasticsearch. You can craft an Elasticsearch or Solr query. Roles who would enjoy this training:
- Search Engineers
- Data Scientists
- Data Engineers that use the search engine
- Machine learning engineers
- Relevance engineers
- Product team wanting exposure to machine learning methods for improving relevance
Quotes From Past Attendees:
"'Hello LTR' training gave me strong conceptual foundation of Learning to Rank and its moving parts, practical tips and learnings on how to implement it in production"
“I’ve been to lots of search trainings and this was by far the best. Not only did you thoroughly cover each aspect of LTR, but you also gave us a crazy amount of jupyter notebooks (in hello-ltr) that really improved the training … I found the jupyter notebooks to be a great way to understand the material.”
Buy Tickets Want training for your team/town? check this out!
“This training in LTR was comprehensive and balanced both theoretical concepts with practical ‘how to’ “. “I will definitely be bringing a lot of the learnings back to my company.”