Hello LTR – Learning to Rank Training

In this two part training course 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 who need Learning to Rank training. Some familiarity with a search engine is expected.

If you’ve already attended our Think Like a Relevance Engineer course – contact us for a discount on Hello LTR!

Who we are

OpenSource Connections believes in empowering search teams. OpenSource Connections has worked with open source search and applied Information Retrieval since 2007. We wrote the book Relevant Search and have pioneered open source relevance tuning tools like the Elasticsearch Learning to Rank plugin, Quepid and Splainer.

Your trainer

Your OpenSource Connections trainer is a relevance thought-leader actively working on real-life relevance issues. Learning to Rank training is core to our mission of ‘empowering search teams’, so you get our best and brightest. We never send a trainer to just “read off slides”. We expect you to bring your hardest questions to our trainers. Our trainers expect to be challenged, and know how to handle unique twists on problems they’ve seen before.

What you’ll get out of it

How to:

• Interact with the Solr & Elasticsearch Learning to Rank plugins
• Use machine learning to optimize relevance
• Avoid common pitfalls on Learning to Rank projects
• Avoid ‘garbage-in, garbage out’ – generating great features and training data
• Hands-on work with Learning to Rank models
• Integrate click models and conversions to generate meaningful training data

Part One: Hands on Basics

(delivered over 2 half days online or one day in person)

We get hands on with movie data, and a simple judgment list. We see where things can go wrong!

• Search Relevance as an Machine Learning Problem
• Cutting your Teeth With Your First Model
• What’s Wrong with My Judgments?
• Iterating on Features
• Choosing the Best Learning to Rank Model

Part Two: Real-World Learning to Rank

(delivered over 2 half days online or one day in person)

At scale, in a real search applications, here are the concerns that will rear themselves:

• Dealing with Presentation Bias
• Including Non-User Relevance Concerns (Business Rules and Marketplace concerns)
• Model Verification, Checks, and Balances
• Personalization and Recommendations with Learning to Rank
• Including Embeddings and Other Exotic Features
• The Next Frontiers of ML and Search

Who should come to Learning to Rank training?

This training is appropriate for members of the search team that have an interest in optimizing search with advanced programming techniques and machine learning:

• Search Engineers
• Data Scientists
• Data Engineers that use the search engine
• Machine learning engineers
• Relevance engineers
• Product team wanting exposure to machine learning methods