BBVA/mercury-monitoring

mercury-monitoring is a library to monitor data and model drift

32
/ 100
Emerging

This library helps data scientists and machine learning engineers monitor the health of their deployed machine learning models. It takes in recent operational data and compares it against historical data used to train the model, outputting whether the data patterns have shifted or if the model's performance has degraded, even without true labels. This allows practitioners to proactively address issues like retraining models or triggering alerts.

Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Use this if you need to automatically detect when the input data to your machine learning models changes, or when your models start to perform worse in production, allowing you to maintain model accuracy and reliability.

Not ideal if you are looking for a fully managed, plug-and-play monitoring solution that doesn't require any coding or integration effort.

model-monitoring data-drift-detection machine-learning-operations predictive-analytics data-quality-assurance
Stale 6m
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 12, 2025

Commits (30d)

0

Dependencies

7

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BBVA/mercury-monitoring"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.