What is it about?
Machine learning is used for a wide variety of projects in industry, but it is also commonly involved in projects that fail to be implemented. These failures are often due to an inability of the machine learning component to achieve a level of performance that will satisfy the business goals. These problems could be mitigated by a greater awareness of how well a model needs to perform in advance of the project work. This research presents an open source package for estimating the required model performance characteristics from a set of data points about the business process it will be applied to.
Featured Image
Photo by ray rui on Unsplash
Why is it important?
Use of the MinViME tool and research can assist those working in applied machine learning to be better prepared for successful delivery of machine learning models that deliver an impact.
Read the Original
This page is a summary of: MinViME/Minimum Viable Model Estimator, Software Impacts, August 2021, Elsevier,
DOI: 10.1016/j.simpa.2021.100073.
You can read the full text:
Contributors
The following have contributed to this page
