***SEATS ARE VERY LIMITED (12), Preference given to techfrederick members***
Training: Learning to Rank
Date: July 6 – 9, 2020 9am-1pm
Location: Your remote workspace
Instructors: Open Source Connections, Doug Turbull
Cost: $100, payment link will be sent upon application approval
*** As this training is funded by State of MD EARN Grant funding, the information requested throughout the registration and participation process is REQUIRED by the State of Maryland for their tracking and statistical purposes. ***
Perhaps your team has done what it can with normal relevance methods and now wants to move towards using Machine Learning to optimize search relevance?
Learning to Rank training course will give your team the ability to use open source Machine Learning tools to improve search relevance. This class helps you understand how to work with Solr/Elasticsearch’s Learning to Rank plugins, train models, avoid common pitfalls, learn how to carry out feature engineering, and how to generate high quality training data from user search behavior.
Tech Frederick has once again partnered with Open Source Connections for this training. OpenSource Connections has worked with open source search and applied Information Retrieval since 2007. OSC’s Doug Turnbull wrote the book ‘Relevant Search’, THE book on search relevance, and they have pioneered tools like the Elasticsearch Learning to Rank plugin, Quepid, Splainer, and other open source relevance tools.
In this 4 half-days course, attendees will:
- 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 conversations to generate meaningful training data
This course is intended for:
- Experienced Search Engineers
- Experienced Data Scientists
- Experienced Machine Learning Engineers
- Attendees should have experience with Elasticsearch/Solr and contribute to the search functions within their organizations