This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
View analytic
Friday, October 14 • 1:10pm - 1:50pm
Customizing Ranking Models in Solr to improve relevance for Enterprise Search
Solr provides a suite of built-in capabilities that offers a wide variety of relevance related parameter tuning. Index and/or query time boosts along with function queries can provide a great way to tweak various relevance related parameters to help improve the search results ranking. In the enterprise space however, given the diversity of customers and documents, there is a much greater need to be able to have more control over the ranking models and be able to run multiple custom ranking models.

At Salesforce, we have a multi-level ranking pipeline, first ranker (L1), is the basic lucene scoring based on tf-idf and the second ranker (L2), implements more complex ranking models ranging from something as trivial as a linear regression to the more complex models such as a boosted decision tree. This L2 ranker inside Solr enables us to extract features for every document from within the Solr Index and leverage them during ranking model execution. This talk discusses the motivation behind creating an L2 ranker and the use of Solr Search Component for running different types of ranking models.

avatar for Ammar Harris

Ammar Harris

Lead Member Technical Staff, Search Relevance, Salesforce
Ammar is a member of the Search Relevance team at Salesforce for over two years. He has been working with the team to build out a new framework for Salesforce Search that would enable the team to train\test, experiment and ship multiple relevance models to production. Prior to joining Salesforce he worked for about six years in Microsoft, primarily in the BingAds and Xbox Games Studio teams.
avatar for Joe Zeimen

Joe Zeimen

Senior Member of Technical Staff, Salesforce
Joe currently works on the Search Relevance team at Salesforce. He is helping to build out a new framework for Salesforce Search that enables the team to train, test and ship different relevance models to production. Prior to joining Salesforce over 3 years ago he earned his BS/MS in Computer Science at the Colorado School of Mines.

Friday October 14, 2016 1:10pm - 1:50pm
Back Bay B Sheraton Boston