Challenges in Deploying Machine Learning: A Survey of Case Studies

被引:147
作者
Paleyes, Andrei [1 ]
Urma, Raoul-Gabriel [2 ]
Lawrence, Neil D. [1 ]
机构
[1] Univ Cambridge, Dept Comp Sci & Technol, Cambridge, England
[2] Cambridge Spark, Cambridge, England
基金
英国科研创新办公室;
关键词
Machine learning applications; sofware deployment; DEPLOYMENT; CLASSIFICATION; TECHNOLOGIES;
D O I
10.1145/3533378
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In recent years, machine learning has transitioned from a field of academic research interest to a field capable of solving real-world business problems. However, the deployment of machine learning models in production systems can present a number of issues and concerns. This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries, and applications and extracts practical considerations corresponding to stages of the machine learning deployment workflow. By mapping found challenges to the steps of the machine learning deployment workflow, we show that practitioners face issues at each stage of the deployment process. The goal of this article is to lay out a research agenda to explore approaches addressing these challenges.
引用
收藏
页数:29
相关论文
共 159 条
  • [1] Abedjan Z, 2016, PROC VLDB ENDOW, V9, P993
  • [2] Deploying Machine Learning Models for Public Policy: A Framework
    Ackermann, Klaus
    Walsh, Joe
    De Unanue, Adolfo
    Naveed, Hareem
    Rivera, Andrea Navarrete
    Lee, Sun-Joo
    Bennett, Jason
    Defoe, Michael
    Cody, Crystal
    Haynes, Lauren
    Ghani, Rayid
    [J]. KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 15 - 22
  • [3] Health-Care Data Collecting, Sharing, and Using in Thailand, China Mainland, South Korea, Taiwan, Japan, and Malaysia
    Aljunid, Syed Mohamed
    Srithamrongsawat, Samrit
    Chen, Wen
    Bae, Seung Jin
    Pwu, Raoh-Fang
    Ikeda, Shunya
    Xu, Ling
    [J]. VALUE IN HEALTH, 2012, 15 (01) : S132 - S138
  • [4] Software Engineering for Machine Learning: A Case Study
    Amershi, Saleema
    Begel, Andrew
    Bird, Christian
    DeLine, Robert
    Gall, Harald
    Kamar, Ece
    Nagappan, Nachiappan
    Nushi, Besmira
    Zimmermann, Thomas
    [J]. 2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: SOFTWARE ENGINEERING IN PRACTICE (ICSE-SEIP 2019), 2019, : 291 - 300
  • [5] AML Team, 2016, Conference on Predictive APIs and Apps, P1
  • [6] Ananth Ram, 2019, CISC VIS NETW IND GL
  • [7] Artificial intelligence in the creative industries: a review
    Anantrasirichai, Nantheera
    Bull, David
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2022, 55 (01) : 589 - 656
  • [8] [Anonymous], 2019, STATE DEV OPERATIONS
  • [9] [Anonymous], 2019, DIMENS RES
  • [10] Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
    Ashmore, Rob
    Calinescu, Radu
    Paterson, Colin
    [J]. ACM COMPUTING SURVEYS, 2021, 54 (05)