Haystack Europe 2019

The Search Relevance Conference! Sponsored by OpenSource Connections

Back to Haystack EU 2019


Deep, technical talks covering search relevance challenges & solutions.

Watch videos of all the talks on our YouTube channel or select an individual talk from the list below.

9:00-9:45 Haystack Europe 2019 Keynote

Keynote for Europe 2019

9:45-10:30 Improving precision of e-commerce search results to generate value for customers and business

This talk will discuss Otto.de's journey to improve search relevance for its customers

10:30-10:45 Break
10:45-11:30 Balancing the Dimensions of User Intent

The first step in returning relevant search results is successfully interpreting the user's intent. This requires combining a holistic understanding of your content, your users, and your domain.

11:30-12:15 Query Intelligence: Understanding User Intent

EBSCO Health's Search Team applies user intent analysis to increase precision and reduce the time to answer critical medical questions.

12:15-13:15 Lunch
13:15-14:00 Search to Search recommendations (Collaborative Synonym and Spell corrections)

We developed an item-item collaborative recommendation algorithm derived from markov chains and co-occurrences in order to take advantage of anonymous sessions data as implicit feedback.

14:00-14:45 Relevant Facets

This talk is an exhaustive presentation around facets and how to make them relevant. Which facets to display and when, how to handle unstructured data, what's the best user experience in each use case

14:45-15:00 Break
15:00-15:45 Ranking article comments using reinforcement learning

In this talk we'll show how ranking user comments on Yahoo properties was solved using reinforcement learning at serving time on Yahoo content sites, using the Vespa open source platform to create a scalable production solution.

15:45-16:30 How to Kill Two Birds with One Stone: Learning to Rank with Multiple Objectives

Zalando discusses and compares several approaches to solving this problem paying special attention to the LambdaMART framework

16:30-17:00 Parting Words