BBVA/mercury-monitoring
mercury-monitoring is a library to monitor data and model drift
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.
Stars
15
Forks
—
Language
Jupyter Notebook
License
Apache-2.0
Category
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.
Higher-rated alternatives
online-ml/river
🌊 Online machine learning in Python
IFCA-Advanced-Computing/frouros
Frouros: an open-source Python library for drift detection in machine learning systems.
NannyML/nannyml
nannyml: post-deployment data science in python
Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics
Implementation/Tutorial of using Automated Machine Learning (AutoML) methods for static/batch...
etsi-ai/etsi-watchdog
Real-time data drift detection and monitoring for machine learning pipelines.