John Berryman and Doug Turnbull, authors of Relevant Search, reunite to give talks on using Machine Learning to improve search relevance.
Talk 1: Elasticsearch Learning to Rank: Search as a Machine Learning Problem
Doug Turnbull, one of the creators of the “Elasticsearch Learning to Rank Plugin” and author of Relevant Search, will discuss how search can be treated as a machine learning problem. ‘Learning to Rank’ takes the step to returning optimized results to users based on patterns in usage behavior. We will talk through where Learning to Rank has shined, as well as the limitations of a machine learning based solution to improve search relevance.
In conjunction with this meetup, Doug Turnbull is delivering a hands on, small group Elasticsearch relevance workshop at the Eventbrite offices in San Francisco. He’d love to invite anyone from the Elastic meetup to participate.
Talk 2: Search Logs + Machine Learning = Auto-Tagged Inventory
John Berryman’s team at Eventbrite is investigating using a combination of customer interactions and machine learning to automatically tag and categorize our inventory for search. As customers interact with the platform - as they search for events and click on and purchase events that interest them - the software implicitly gathers information about how users think about our inventory. Search text effectively acts like a tag and a click on an event card is a vote for that clicked event is representative of that tag. Eventbrite is able to use this stream of information as training data for a machine learning classification model; and as the software receives new inventory, it can automatically tag the event with the text that customers will likely use when searching for the event.
In this talk John will explain in depth the problem space and Eventbrite’s approach in solving the problem.