of hand labeling replaced in a few hours using Snorkel
Rapidly build, adapt, and deploy agile anomaly detection applications.
Faster, Lower-cost Development
Use programmatic labeling to develop high-quality AI applications in hours instead of spending weeks or months on expensive hand-labeling.
Monitor for changes in the data, and rapidly adapt using built-in error analysis tools. Zoom in on errors to fine-tune training data & models with guided iteration.
Leverage large amounts of labeled and unlabeled data, and state-of-the-art anomaly detection model architectures to build high-accuracy anomaly detectors.
Easily integrate labeling, training, and analysis pipelines defined over diverse input types–text, PDF, HTML, and more–with downstream applications using APIs or a Python SDK.
Explore Enterprise Solutions For Anomaly Detection
Banks can identify accounts with unusual deposit behavior for potential money laundering.
TELECOM & CYBER
Cybersecurity firms can detect anomalous internet traffic and alert organizations of suspicious activity.
Claims Fraud Detection
Insurance firms can monitor documents to identify potentially spurious claim behavior.
Software companies can detect periods with high or low website visits to understand the root cause.
E-commerce sites can detect incidents in logs and prevent the impact of lost revenue, or poor customer satisfaction scores.
Hospitals can detect anomalies in patient health records to find potentially problematic medical conditions.
Banks can automatically identify and rapidly react to potentially fraudulent account behavior.
Labeling training data for triaging models took person-months to person-years of radiologist time.
Developed a cross-modal, anomaly detection application using Snorkel, matching or exceeding the performance of painstakingly gathered manual labels in hours.
Currently being tested for deployment in Stanford Health & Department of Vetaran Affairs (VA) hospital systems.
of hand-labeling replaced by a few hours
ROC AUC Performance
images labeled in minutes
How Snorkel Flow Works
Build agile anomaly detection applications that identify even rare occurrences in mountains of data. Eliminate onerous hand-annotation processes by programmatically labeling data with powerful labeling functions. Adjust data sampling to zero in on a rare class and augment data using class-aware tooling. Train state-of-the-art models and analyze performance using flexible tools for class-imbalanced problems. Deploy and integrate anomaly detection applications with other data tasks.
An End-to-end ML Platform
Designed for Collaboration
Data Scientist Friendly
- Integrated Jupyter notebooks
- Instant analysis tools
- Ready-to-use models
Domain Expert Friendly
- Intuitive, no-code UI
- Rich dashboards and visualizations
- Full-featured, push-button error analysis
- Platform access via Python SDK
- Online or batch API deployment
- Containerized software for cloud or on-premises deployments
Weakly Supervised Classification of Aortic Valve Malformations Using …J. Fries, et al. Nature Comms 2019
The Role of Massively Multi-Task and Weak Supervision in Software 2.0A. Ratner, et al, CIDR 2019