A better way to
monitor ML models

Monitor what matters. Find what is broken. Fix it.
Everything, without ground truth.

Get Started Get a Demo

$ pip install nannyml

content_copy

Trusted by data scientists at

Explore the nannyML way

1

Monitor what matters

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

estimate_performance.py

1 2 3 4 5

import nannyml as nml
estimator = nml.CBPE(...)
estimator.fit(reference_df)
results = estimator.estimate(analysis_df)
results.plot()

Video interaction of estimating post-deployment model performance

swap_driving_apps_wheel

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.

attach_money

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.

warning

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 Started Learn More

2

Find what is broken

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

calculate_drift.py

1 2 3 4 5

import nannyml as nml
calc = nml.UnivariateDriftCalculator(...)
cal.fit(reference_df)
results = calc.calculate(analysis_df)
results.plot()

bolt

Faster root cause analysis

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

analytics

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.

lightbulb