☂
What is NannyML Cloud?
Use NannyML OSS for free. Upgrade to NannyML Cloud to monitor without the hassle, enable enhanced security controls, and access additional features.
✅ 5 minutes to configure your models. Effortless Observability.
✅ Early access to concept drift detection. Most powerful nannyML algorithm yet.
✅ Reporting and dashboarding handled. Always know how your models are performing.
✅ Deployed in your cloud. Safe and Secure
✅ Infrastructure, alerting, and scheduling. Automated. Focus on what matters.
https://storage.tally.so/7f1610dc-5f2d-4507-adab-61f643dc343b/Screenshot-2023-08-07-at-16.09.34.png
NannyML Cloud is a web-based solution for monitoring machine learning models. It is based on the open-source NannyML Python library. With NannyML, you can: monitor what matters, find what is broken, and fix it. Everything, even without ground truth.
- Monitoring for all model types on tabular data, also when ground truth is not available in production
- Flagship algorithms for concept drift, performance estimation, and multivariate drift detection
- Get alerted when model performance changes
- Available in Azure Market Place (AWS coming soon)
Focus on one single metric to know how your model is performing. And get alerted when the performance drops.
- 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 your model's performance to monetary or business-oriented outcomes. So that you always know what your ML brings to the table.
- Avoid alert fatigue Traditional ML monitoring tends to overwhelm teams with many false alarms. By focusing on what matters, NannyML alerts are always meaningful.
- Root Cause Analysis The univariate drift detection methods allow us to perform a granular investigation across the model's features.
- Uncover the most subtle changes in the data structure Leverage the multivariate drift detection method to uncover changes univariate approaches cannot detect.
- Intelligent alert ranking NannyML links back data drift alerts to changes in the model performance. So you can easily detect which features are causing the performance issues.
NannyML Cloud is a web-based solution made by the creators of the open-source NannyML Python library. Most NannyML Cloud core algorithms are open-source, so you can trust them and be 100% sure how they work.
Built for data scientists, NannyML has an easy-to-use interface and interactive visualizations, is completely model-agnostic, and currently supports all tabular use cases, classification, and regression.
Performance Monitoring
- Performance Estimation
- Performance Calculation
- Business Value Quantization
- Scikit-Learn Metrics
- Custom Metrics
Root cause analysis
- Concept Drift Detection
- Prediction Drift Detection
- Target Drift Detection
- Multivariate Drift Detection
- Univariate Drift Detection
- Advanced Drift Detection
- Data Quality Issue Detection
- Issue Ranking
Issue Resolution
- Custom Thresholds
- Automated Thresholds
- Custom Granularity
- Email & Slack Notifications
- Custom Webhook Actions
- Retraining Triggers
- API Access
Last modified 1mo ago