Cohort Modeling for Enhanced Personalized Search

Web search engines utilize behavioral signals to develop search ex-periences tailored to individual users. To be effective, such person-alization relies on access to sufficient information about each user’s interests and intentions. For new users or new queries, profile in-formation may be sparse or non-existent. To handle these cases, and perhaps also improve personalization for those with profiles, search engines can employ signals from users who are similar along one or more dimensions, i.e., those in the same cohort. In this paper we describe a characterization and evaluation of the use of such cohort modeling to enhance search personalization. We experiment with three pre-defined cohorts—topic, location, and top-level domain preference—independently and in combination, and also evaluate methods to learn cohorts dynamically. We show via extensive ex-perimentation with large-scale logs from a commercial search en-gine that leveraging cohort behavior can yield significant relevance gains when combined with a production search engine ranking al-gorithm that uses similar classes of personalization signal but at the individual searcher level. Additional experiments show that our gains can be extended when we dynamically learn cohorts and tar-get easily-identifiable classes of ambiguous or unseen queries