ML-Enabled Systems Model Deployment and Monitoring: Status Quo and Problems
Authors:
- Eduardo ZimelewiczEZEduardo Zimelewicz
- Marcos KalinowskiMKMarcos Kalinowski
- Daniel MendezDMDaniel Mendez
- Görkem GirayGGGörkem Giray
- Antonio Pedro Santos AlvesAAAntonio Pedro Santos Alves
- Niklas LavessonNiklas Lavesson
- Kelly AzevedoKAKelly Azevedo
- Hugo VillamizarHVHugo Villamizar
- Tatiana EscovedoTETatiana Escovedo
- Helio LopesHLHelio Lopes
- Stefan BifflSBStefan Biffl
- Juergen MusilJMJuergen Musil
- 12 April 2024
- book chapter
- Published by Springer Nature
- p. 112-131
Abstract
No abstract availableKeywords
This publication has 34 references indexed in Scilit:
- Monitoring machine learning models: a categorization of challenges and methodsData Science and Management, 2022
- Architecting AI Deployment: A Systematic Review of State-of-the-Art and State-of-Practice Literature2021
- Why AI/Data Science Projects Fail2021
- Fall detection in older adults with mobile IoT devices and machine learning in the cloud and on the edgeInformation Sciences, 2020
- Challenges in Survey Research2020
- A machine learning model for improving healthcare services on cloud computing environmentMeasurement, 2018
- Naming the pain in requirements engineeringEmpirical Software Engineering, 2016
- Automating and Evaluating Probabilistic Cause-Effect Diagrams to Improve Defect Causal AnalysisLecture Notes in Computer Science, 2011
- Applying DPPI: A Defect Causal Analysis Approach Using Bayesian NetworksLecture Notes in Computer Science, 2010
- An Introduction to the Bootstrap1993