Microsoft Recommenders: Best Practices for Production-Ready Recommendation Systems

被引:18
|
作者
Argyriou, Andreas [1 ]
Gonzalez-Fierro, Miguel [1 ]
Zhang, Le [2 ]
机构
[1] Microsoft, London, England
[2] Microsoft, Singapore, Singapore
关键词
Recommender systems; Algorithms; Libraries;
D O I
10.1145/3366424.3382692
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recommendation algorithms have been widely applied in various contemporary business areas, however the process of implementing them in production systems is complex and has to address significant challenges. We present Microsoft Recommenders, an open-source Github repository for helping researchers, developers and non-experts in general to prototype, experiment with and bring to production both classic and state-of-the-art recommendation algorithms. A focus of this repository is on best practices in development of recommendation systems. We have also incorporated learnings from our experience with recommendation systems in production, in order to enhance ease of use; speed of implementation and deployment; scalability and performance.
引用
收藏
页码:50 / 51
页数:2
相关论文
共 50 条
  • [1] A production-ready silicon microvalve
    Wang, TK
    Barth, P
    Alley, R
    Baker, J
    Yates, D
    Field, L
    Gordon, G
    Beatty, C
    Tully, L
    [J]. MICROMACHINED DEVICES AND COMPONENTS V, 1999, 3876 : 227 - 237
  • [2] "FLYING BUM" IS PRODUCTION-READY
    不详
    [J]. MECHANICAL ENGINEERING, 2019, 141 (04) : 27 - 27
  • [3] Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems
    Challa, Ashwini
    Upasani, Kartikeya
    Balakrishnan, Anusha
    Subba, Rajen
    [J]. 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES(NAACL HLT 2019), VOL. 2 (INDUSTRY PAPERS), 2019, : 214 - 225
  • [4] Finally, behavioral synthesis is production-ready
    Tuck, B
    [J]. COMPUTER DESIGN, 1997, 36 (07): : 57 - +
  • [5] Automakers turn to production-ready printable parts
    Weber, Austin
    [J]. Assembly, 2019, 62 (03):
  • [6] GeoEngine: A Platform for Production-Ready Geospatial Research
    Verma, Sagar
    Gupta, Siddharth
    Shin, Hal
    Panigrahi, Akash
    Goswami, Shubham
    Pardeshi, Shweta
    Exe, Natanael
    Dutta, Ujwal
    Joshi, Tanka Raj
    Bhojwani, Nitin
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 21384 - 21392
  • [7] Production-ready component design for additive manufacturing
    Schwalme, G.
    [J]. VDI Berichte, 2019, (4354):
  • [8] Microsoft Recommenders Tools to Accelerate Developing Recommender Systems
    Graham, Scott
    Min, Jun-Ki
    Wu, Tao
    [J]. RECSYS 2019: 13TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, 2019, : 542 - 543
  • [9] Why Is It Not Solved Yet? Challenges for Production-Ready Autoscaling
    Straesser, Martin
    Grohmann, Johannes
    Von Kistowski, Joakim
    Eismann, Simon
    Bauer, Andre
    Kounev, Samuel
    [J]. PROCEEDINGS OF THE 2022 ACM/SPEC INTERNATIONAL CONFERENCE ON PERFORMANCE ENGINEERING (ICPE '22), 2022, : 105 - 115
  • [10] Challenges Towards Production-Ready Explainable Machine Learning
    Veiber, Lisa
    Allix, Kevin
    Arslan, Yusuf
    Bissyande, Tegawende F.
    Klein, Jacques
    [J]. PROCEEDINGS OF THE 2020 USENIX CONFERENCE ON OPERATIONAL MACHINE LEARNING (OPML '20), 2020, : 21 - 23