What is it about?
This paper explains the different ways that the performance of a machine learning model can degrade over time. It also gives an overview of the software components that need to be developed in order to have an effective performance monitoring solution.
Featured Image
Why is it important?
If successful, the presented project will enable data scientists to deploy a scalable system for ML performance monitoring, without having to worry about technical details.
Perspectives
Going from a machine learning model created in a local environment to a production-ready deployment can take quite a bit of effort. By reducing the effort required for such a transition, we hope to enable teams with limited resources or even individuals to achieve more.
Panagiotis Kourouklidis
University of York
Read the Original
This page is a summary of: Towards a low-code solution for monitoring machine learning model performance, October 2020, ACM (Association for Computing Machinery),
DOI: 10.1145/3417990.3420196.
You can read the full text:
Contributors
The following have contributed to this page
