Anomaly Detection




Rapidly build high-accuracy, adaptive anomaly detection models over documents, logs, network traffic, and more, without hand-labeling training data using Snorkel Flow.

Request demo

Image





Technology developed and deployed with the world’s leading organizations
Image
Image
Image
Image
Image
Image
Image
Image



Overview —

Detect Needles in the Data Stack


Rapidly build, adapt, and deploy agile anomaly detection applications.



Image
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.
Image
Rapidly Adaptable
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.
Image
High-accuracy Models
Leverage large amounts of labeled and unlabeled data, and state-of-the-art anomaly detection model architectures to build high-accuracy anomaly detectors.
Image
Flexible Integrations
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.






Industry Use Cases —

Explore Enterprise Solutions For Anomaly Detection


Build industry-specific AI applications combining state-of-the-art machine learning approaches with industry-specific best practices and last-mile connectors, all on an enterprise-scale platform.



FINANCIAL SERVICES



Contract Intelligence

Banks can classify contracts by terms and conditions to smoothly ensure regulatory complience.
TELECOM & CYBER



Customer Segmentation

Telecom organizations can classify customer usage documents to target promotional offers.
HEALTHCARE



Clinical Trial Matching

Biotech organizations can classify patient records to identify actionable clinical trial candidates.
INSURANCE



Risk Classification

Insurance underwriters can classify piolicy documents by behavioral or occupational variables to assess risk.
SOFTWARE



Search Engine Optimization

Software companies can recognize named entities in customer search queries and to optimize website content.
RETAIL



Product Recommendation

E-commerce sites can recognize entities in product descriptions (price, key words, etc.) to improve recommender systems.






Case Study —

Image
Stanford Medicine used Snorkel to detect medical anomalies using cross-modal data from radiographs, tomographs & monitoring devices, replacing months of hand labeling with few hours of programmatic data creation.



Problem




Labeling training data for triaging models took person-months to person-years of radiologist time.

Solution




Developed a cross-modal, anomaly detection application using Snorkel, matching or exceeding the performance of painstakingly gathered manual labels in hours.

Results




Currently being tested for deployment in Stanford Health & Department of Vetaran Affairs (VA) hospital systems.

8
Person-months of labeling replaced
<0hrs
To develop the first custom ML model
94%
ROC AUC Performance
+0%
Accuracy for contract classification
50K+
Images labeled in minutes
0K
Contracts processed in minutes

Read more






An End-to-end ML Platform —

Designed for Collaboration




Image

Data Scientist Friendly


  • Integrated Jupyter notebooks
  • Guided error analysis
  • Ready-to-use models
Image

Domain Expert Friendly


  • Intuitive, no-code UI
  • Rich dashboards and visualizations
  • Full-featured, push-button error analysis
Image

Developer Friendly


  • Platform access via Python SDK
  • Online or batch API deployment
  • Containerized software for cloud or on-premises deployments






Resources —

Explore More About Snorkel


Learn more about groundbreaking techniques for programmatic labeling and weak supervision developed by Team Snorkel and the broader data science community.



NATURE COMMS

Weakly Supervised Classification of Aortic Valve Malformations Using …

J. Fries, et al, 2019
IEEE IVS

Utilizing Weak Supervision to Infer Complex Objects in Autonomous Driving…

Z. Wheng, et al, 2019
MEDIUM

Understanding Snorkel

Anna Zubova
Research Paper

Trove: Ontology-driven Weak Supervision for
Medical Entity Classification

J. Fries, et al. 2020
AAAI

Training Complex Models with Multi-Task Weak Supervision

A. Ratner, et al, 2019
ACL

Training Classifiers with Natural Language Explanations

B. Hancock, et al, 2018
Research Paper

Train and You’ll Miss It: Interactive Model Iteration with Weak Supervision…

M. Chen, et al, 2020
CIDR

The Role of Massively Multi-Task and Weak Supervision in Software 2.0

A. Ratner, et al, 2019
FAST FOWARD LABS

Taking Snorkel for a Spin

Fast Forward Labs at Cloudera
Research Paper

SwellShark: A Generative Model for Biomedical NER without Labeled Data

J. Fries, et al, 2017
AI4 CYBER SUMMIT

State of AI in Cyber

Ai4 Cyber Summit
Course

Stanford University: CS229 – Machine Learning

Chris Re