Litcius/Paper detail

A Model-Driven Engineering Approach for Monitoring Machine Learning Models

Panagiotis Kourouklidis, Dimitrios S. Kolovos, Joost Noppen, Nicholas Matragkas

20212021 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C)17 citationsDOIOpen Access PDF

Abstract

Once a machine learning (ML) model is produced and used for commercial purposes, it is desirable to continuously monitor it for any potential performance degradation. Domain experts in the area of ML, commonly lack the required expertise in the area of software engineering, needed to implement a robust and scalable monitoring solution. This paper presents an approach based on model-driven engineering (MDE) principles, for detecting and responding to events that can affect a ML model’s performance. The proposed solution allows ML experts to schedule the execution of drift detecting algorithms on a computing cluster and receive email notifications of the outcome without requiring extensive software engineering knowledge.

Topics & Concepts

Computer scienceScalabilityScheduleModel-driven architectureDomain (mathematical analysis)Domain engineeringSoftware engineeringSoftwareMachine learningComponent-based software engineeringSoftware developmentOperating systemMathematicsMathematical analysisData Stream Mining TechniquesMachine Learning and Data ClassificationAnomaly Detection Techniques and Applications