Using A Query Classifier To Dynamically Boost Solr Ranking
As we countdown to the annual Lucene/Solr Revolution conference in Las Vegas next month, we’re highlighting talks and sessions from…
As we countdown to the annual Lucene/Solr Revolution conference in Las Vegas next month, we’re highlighting talks and sessions from past conferences. Today, we’re highlighting Target’s Howard Wan’s talk, “Using A Query Classifier To Dynamically Boost Solr Ranking”.
About 40% of our queries at Target.com are ambiguous, which can result in products from many categories. For example, the query “red apple” can match the following products: a red apple ipod (electronic category), red apple fruit ( fresh produce ), 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 a 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.
Join us at Lucene/Solr Revolution 2017, the biggest open source conference dedicated to Apache Lucene/Solr on September 12-15, 2017 in Las Vegas, Nevada. Come meet and network with the thought leaders building and deploying Lucene/Solr open source search technology. Full details and registration…