Expert-Driven Monitoring of Operational ML Models

Joran Leest; Claudia Raibulet; Ilias Gerostathopoulos; Patricia Lago

Expert-Driven Monitoring of Operational ML Models

Machine Learning 2024-01-23 v1 Software Engineering

Authors: Joran Leest , Claudia Raibulet , Ilias Gerostathopoulos , Patricia Lago

Abstract

We propose Expert Monitoring, an approach that leverages domain expertise to enhance the detection and mitigation of concept drift in machine learning (ML) models. Our approach supports practitioners by consolidating domain expertise related to concept drift-inducing events, making this expertise accessible to on-call personnel, and enabling automatic adaptability with expert oversight.

Keywords

concept drift machine learning monitoring domain expertise expert-driven automatic adaptability operational ML models

Cite

@article{arxiv.2401.11993,
  title  = {Expert-Driven Monitoring of Operational ML Models},
  author = {Joran Leest and Claudia Raibulet and Ilias Gerostathopoulos and Patricia Lago},
  journal= {arXiv preprint arXiv:2401.11993},
  year   = {2024}
}

Related papers

View all related →