Loading…
Back To Schedule
Friday, October 14 • 10:30am - 11:10am
Using a Query Classifier to dynamically boost Solr ranking
Tweet Share
About 40% of our queries are ambiguous, which can result with products from many categories. For example, the query "red apple" can match the following products:

1. red apple ipod (electronic category)
2. red apple fruit ( fresh produce )
3. red apple iphone case ( accessories)

It is desirable to have a classifier to instruct Solr to boost items from the desire category. In addition, for a search engine with small index, a good percentage of the queries may have little or no results. Is it possible to use the classifier to solve both problems?

This talk discusses a classifier built from behavior data which can dynamically re-classify the query to solve both problems.
Speakers
avatar for Howard Wan

Howard Wan

Dev Manager, Target
How is a Dev manager of the Query Intent team at Target. His prior experience included Ebay and Microsoft search engine development. He has several search patent application for all three companies. His passion is search relevance development and monetization prediction models.

Friday October 14, 2016 10:30am - 11:10am EDT
Commonwealth Sheraton Boston
  Data Science