Demystifying Core Ranking in Pinterest Image Search

Pinterest Image Search Engine helps hundreds of millions of users discover interesting content everyday. This motivates us to improve the image search quality by evolving our ranking techniques. In this work, we share how we practically design and deploy various ranking pipelines into Pinterest imag...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Author Zhu, Linhong
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.03.2018
Subjects
Comparative analysis
Image quality
Ranking
Search engines
Software reviews
Online AccessGet full text

Cover

More Information
Summary:Pinterest Image Search Engine helps hundreds of millions of users discover interesting content everyday. This motivates us to improve the image search quality by evolving our ranking techniques. In this work, we share how we practically design and deploy various ranking pipelines into Pinterest image search ecosystem. Specifically, we focus on introducing our novel research and study on three aspects: training data, user/image featurization and ranking models. Extensive offline and online studies compared the performance of different models and demonstrated the efficiency and effectiveness of our final launched ranking models.
ISSN:2331-8422