Challenges in Machine Learning Deployment: A Survey of Case Studies

Andrei Paleyes, Raoul-Gabriel Urma, Neil D. Lawrence
ACM Comput. Surv., Association for Computing Machinery , 2022.

Abstract

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 paper is to lay out a research agenda to explore approaches addressing these challenges.

Cite this Paper

BibTeX
@Article{challenges-in-deploying-machine-learning-a-survey-of-case-studies, title = {Challenges in Machine Learning Deployment: A Survey of Case Studies}, author = {Paleyes, Andrei and Urma, Raoul-Gabriel and Lawrence, Neil D.}, journal = {ACM Comput. Surv.}, year = {2022}, address = {New York, NY, USA}, publisher = {Association for Computing Machinery}, url = {http://inverseprobability.com/publications/challenges-in-deploying-machine-learning-a-survey-of-case-studies.html}, abstract = {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 paper is to lay out a research agenda to explore approaches addressing these challenges.} }
Endnote
%0 Journal Article %T Challenges in Machine Learning Deployment: A Survey of Case Studies %A Andrei Paleyes %A Raoul-Gabriel Urma %A Neil D. Lawrence %J ACM Comput. Surv. %D 2022 %F challenges-in-deploying-machine-learning-a-survey-of-case-studies %I Association for Computing Machinery %U http://inverseprobability.com/publications/challenges-in-deploying-machine-learning-a-survey-of-case-studies.html %X 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 paper is to lay out a research agenda to explore approaches addressing these challenges.
RIS
TY - JOUR TI - Challenges in Machine Learning Deployment: A Survey of Case Studies AU - Andrei Paleyes AU - Raoul-Gabriel Urma AU - Neil D. Lawrence DA - 2022/04/30 ID - challenges-in-deploying-machine-learning-a-survey-of-case-studies PB - Association for Computing Machinery UR - http://inverseprobability.com/publications/challenges-in-deploying-machine-learning-a-survey-of-case-studies.html AB - 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 paper is to lay out a research agenda to explore approaches addressing these challenges. ER -
APA
Paleyes, A., Urma, R. & Lawrence, N.D.. (2022). Challenges in Machine Learning Deployment: A Survey of Case Studies. ACM Comput. Surv. Available from http://inverseprobability.com/publications/challenges-in-deploying-machine-learning-a-survey-of-case-studies.html.

Related Material