Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models

TL;DR

Amazon SageMaker Model Monitor is a managed service that provides real-time detection of data and concept drift in deployed machine learning models, ensuring ongoing performance and reliability.

Contribution

It introduces a comprehensive system for monitoring various types of model drift in real-time, with practical deployment insights from over two years of use.

Findings

Effective detection of data and concept drift in production

Real-time alerts enable prompt corrective actions

Demonstrated system robustness over two years of deployment

Abstract

With the increasing adoption of machine learning (ML) models and systems in high-stakes settings across different industries, guaranteeing a model's performance after deployment has become crucial. Monitoring models in production is a critical aspect of ensuring their continued performance and reliability. We present Amazon SageMaker Model Monitor, a fully managed service that continuously monitors the quality of machine learning models hosted on Amazon SageMaker. Our system automatically detects data, concept, bias, and feature attribution drift in models in real-time and provides alerts so that model owners can take corrective actions and thereby maintain high quality models. We describe the key requirements obtained from customers, system design and architecture, and methodology for detecting different types of drift. Further, we provide quantitative evaluations followed by use cases, insights, and lessons learned from more than two years of production deployment.