Model Monitoring Best Practices


Lessons from the field on model monitoring best practices

A growing number of decisions and critical business processes rely on models produced with machine learning and other statistical techniques.

For a variety of reasons, the inputs and outputs from these models can “drift” over time, and produce unexpected behavior and a decrease in predictive accuracy. Unfortunately, this drift often goes unrecognized because of inadequate tools or internal processes, leading to severe financial loss or a degraded customer experience.

Download this paper today to learn:

  • The types of data drift that impact machine learning models;
  • How to identify models that are degrading;
  • Five best practices for monitoring models in production; and
  • Recommended next steps for correcting model drift.

This paper represents best practices Domino has learned from 5+ years of working with data science leaders at companies such as Allstate, Bayer, Dell and Moody’s Analytics.

Get the Resource

Latest resources


The Practical Guide to Managing Data Science at Scale


The Forrester Wave™: Notebook-Based Predictive Analytics and Machine Learning, Q3 2020


Kubernetes: The IT Standard for Data Science Workloads


Accelerate Adoption of SAS Data Science Use Cases in the Cloud Using Domino

Dun & Bradstreet seal