🎓 Free introductory course "LLM evaluations for AI product teams". Save your seat

ML Monitoring

5 methods to detect drift in ML embeddings

ML Monitoring

Shift happens: we compared 5 methods to detect drift in ML embeddings

Monitoring embedding drift is relevant for the production use of LLM and NLP models. We ran experiments to compare 5 drift detection methods. Here is what we found.

ML model maintenance. “Should I throw away the drifting features”?

ML Monitoring

ML model maintenance. “Should I throw away the drifting features”?

Imagine you have a machine learning model in production, and some features are very volatile. Their distributions are not stable. What should you do with those? Should you just throw them away?

Pragmatic ML monitoring for your first model. How to prioritize metrics?

ML Monitoring

Pragmatic ML monitoring for your first model. How to prioritize metrics?

There is an overwhelming set of potential metrics to monitor. In this blog, we'll try to introduce a reasonable hierarchy.

Monitoring ML systems in production. Which metrics should you track?

ML Monitoring

Monitoring ML systems in production. Which metrics should you track?

When one mentions "ML monitoring," this can mean many things. Are you tracking service latency? Model accuracy? Data quality? This blog organizes everything one can look at in a single framework.

Which test is the best? We compared 5 methods to detect data drift on large datasets

ML Monitoring

Which test is the best? We compared 5 methods to detect data drift on large datasets

We ran an experiment to help build an intuition on how popular drift detection methods behave. In this blog, we share the key takeaways and the code to run the tests on your data.

Q&A: ML drift that matters. "How to interpret data and prediction drift together?"

ML Monitoring

Q&A: ML drift that matters. "How to interpret data and prediction drift together?"

Data and prediction drift often need contextual interpretation. In this blog, we walk you through possible scenarios for when you detect these types of drift together or independently.

Q&A: Do I need to monitor data drift if I can measure the ML model quality?

ML Monitoring

Q&A: Do I need to monitor data drift if I can measure the ML model quality?

Even if you can calculate the model quality metric, monitoring data and prediction drift can be often useful. Let’s consider a few examples when it makes sense to track the distributions of the model inputs and outputs.

Q&A: What is the difference between outlier detection and data drift detection?

ML Monitoring

Q&A: What is the difference between outlier detection and data drift detection?

When monitoring ML models in production, we can apply different techniques. Data drift and outlier detection are among those. What is the difference? Here is a visual explanation.

Can you build a machine learning model to monitor another model?

ML Monitoring

Can you build a machine learning model to monitor another model?

Can you train a machine learning model to predict your model’s mistakes? Nothing stops you from trying. But chances are, you are better off without it.

Machine Learning Monitoring, Part 5: Why You Should Care About Data and Concept Drift

ML Monitoring

Machine Learning Monitoring, Part 5: Why You Should Care About Data and Concept Drift

No model lasts forever. While the data quality can be fine, the model itself can start degrading. A few terms are used in this context. Let’s dive in.

Machine Learning Monitoring, Part 4: How To Track Data Quality and Data Integrity

ML Monitoring

Machine Learning Monitoring, Part 4: How To Track Data Quality and Data Integrity

A bunch of things can go wrong with the data that goes into a machine learning model. Our goal is to catch them on time.

Machine Learning Monitoring, Part 3: What Can Go Wrong With Your Data?

ML Monitoring

Machine Learning Monitoring, Part 3: What Can Go Wrong With Your Data?

Garbage in is garbage out. Input data is a crucial component of a machine learning system. Whether or not you have immediate feedback, your monitoring starts here.

Machine Learning Monitoring, Part 2: Who Should Care, and What We Are Missing

ML Monitoring

Machine Learning Monitoring, Part 2: Who Should Care, and What We Are Missing

Who should care about machine learning monitoring? The short answer: everyone who cares about the model's impact on business.

Machine Learning Monitoring, Part 1: What It Is and How It Differs

ML Monitoring

Machine Learning Monitoring, Part 1: What It Is and How It Differs

Congratulations! Your machine learning model is now live. Many models never make it that far. Some claim, as much as 87% are never deployed.

Get Started with AI Observability

Book a personalized 1:1 demo with our team or sign up for a free account.

No credit card required

By clicking “Accept”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.