On the Value of ML Models

  • Yang, J. (Speaker)
  • Fabio Casati (Speaker)
  • Pierre-André Noël (Speaker)

Activity: Talk or presentationTalk or presentation at a workshop, seminar, course or other meeting

Description

We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics that better capture the value delivered by their model in practical applications. For a specific class of use cases—selective classification—we show that not only can it be simple enough to do, but that it has import consequences and provides insights what to look for in a “good” ML model.
Period6 Dec 2021
Event titleNeurIPS 2021 Workshop on Human and Machine Decisions
Event typeConference
Conference number34