Corpus ID: 198120381

Production Ranking Systems: A Review

@article{Iqbal2019ProductionRS,
  title={Production Ranking Systems: A Review},
  author={M. Iqbal and Nishan Subedi and Kamelia Aryafar},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.12372}
}
  • M. Iqbal, Nishan Subedi, Kamelia Aryafar
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • The problem of ranking is a multi-billion dollar problem. In this paper we present an overview of several production quality ranking systems. We show that due to conflicting goals of employing the most effective machine learning models and responding to users in real time, ranking systems have evolved into a system of systems, where each subsystem can be viewed as a component layer. We view these layers as being data processing, representation learning, candidate selection and online inference… CONTINUE READING
    1 Citations

    Figures and Topics from this paper

    References

    SHOWING 1-10 OF 58 REFERENCES
    Search Ranking And Personalization at Airbnb
    • 11
    SoftRank: optimizing non-smooth rank metrics
    • 280
    • PDF
    AdaRank: a boosting algorithm for information retrieval
    • 798
    • PDF
    Learning to Rank for Information Retrieval
    • 963
    • PDF
    Recommendations for All: Solving Thousands of Recommendation Problems Daily
    • Bhargav Kanagal, S. Tata
    • Computer Science
    • 2018 IEEE 34th International Conference on Data Engineering (ICDE)
    • 2018
    • 2
    • PDF
    Optimizing search engines using clickthrough data
    • 4,104
    • PDF
    From RankNet to LambdaRank to LambdaMART: An Overview
    • 748
    • PDF
    Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
    • 73
    • Highly Influential
    • PDF
    Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
    • 46
    • Highly Influential
    • PDF