The Elasticsearch Learning to Rank plugin uses machine learning to improve search relevance ranking. It's powering search at places like Wikimedia Foundation and Snagajob.

Features

  • Allows you to store features (Elasticsearch query templates) in Elasticsearch
  • Documentation available
  • Logs features scores (relevance scores) to create a training set for offline model development
  • Stores linear, xgboost, or ranklib ranking models in Elasticsearch that use features you've stored
  • Ranks search results using a stored model
  • You can also participate in regular trainings on Elasticsearch Learning to Rank

Project Samples

elasticsearch-learning-to-rank Screenshot 1

Project Activity

See All Activity >