A better way to
monitor ML models

Monitor what matters. Find what is broken. Fix it.
Everything, without ground truth.
Get StartedGet a Demo
$ pip install nannyml
Trusted by data scientists at
Arise Health logoOE logoOE logoEphicient logoArise Health logoThe Paak logoThe Paak logoEphicient logoEphicient logoEphicient logo
Explore the nannyML way

Monitor what matters

Focus on one single metric to know how your model is performing. And get alerted when the performance drops.

1 2 3 4 5
import nannyml as nml
estimator = nml.CBPE(...)
results = estimator.estimate(analysis_df)
Video interaction of estimating post-deployment model performance

Estimate model performance

Know the performance of your ML models 24/7. NannyML estimates the performance of your ML models. Even if the ground truth is delayed or absent.


Measure the business impact of your models

Tie the performance of your model to monetary or business oriented outcomes. So that you always know what your ML brings to the table.


Avoid alert fatigue

Traditional ML monitoring tend to overwhelm teams with many false alarms. By focusing on what matters NannyML alerts are always meaningful.

Get StartedLearn More

Find what is broken

Understand the root cause of the performance drop in a matter of minutes. Use advanced tools at your disposal.

1 2 3 4 5
import nannyml as nml
calc = nml.UnivariateDriftCalculator(...)
results = calc.calculate(analysis_df)

Faster root cause analysis

Our univariate drift detection methods allow to perform a granular investigation across the model's features.


Uncover the most subtle changes in the data structure

Our multivariate drift detection method uncover changes
that univariate approaches cannot detect. Such as changes in the linear relationships between features. So with one single method you can know if the general distribution of the feature space has changed.


Intelligent alert ranking

NannyML links data drift alerts with the performance changes. So you can easily detect which features are causing the performances issues.

Works with any ML framework
The Paak logo
Get StartedLearn More

Fix it

No more sleepless nights without knowing how your models
are doing.

What Data Science Leaders have to say about NannyML
Start monitoring your models today
pip install nannyml
conda install -c conda-forge nannyml
Learn more about the new way to monitor your ML models
NannyML Logo
The Open Source library for post deployment data science