Our Technology

Leverage DataVisor's cutting-edge approach to detect new and unknown attacks before damage is done.

Request Demo

Designed for the Digital Era

The DataVisor approach combines cutting-edge AI and machine learning technologies to correlate fraudulent and suspicious patterns across billions of accounts in real time. Patented and proprietary unsupervised machine learning (UML) algorithms work without labeled input data to automatically detect new and previously unidentified fraud and abuse patterns.

What is UML?

How the Unsupervised Machine Learning Engine Works

Decisions Without Assumptions

The DataVisor Unsupervised Machine Learning Engine processes all events and account activities simultaneously to analyze patterns across hundreds of millions of accounts. This enables detection of suspicious connections between malicious accounts, even when those accounts are incubating, mimicking legitimate user activities, or changing attack techniques. This also allows the UML Engine to detect all the members of an attack ring at once, ensuring the attack is fully stopped.

Image for Unsupervised Machine Learning Engine
Unsupervised Machine Learning Engine

At the core of the platform is DataVisor’s UML Engine that combines clustering techniques with graph analysis to discover correlated fraudulent and suspicious patterns from unlabeled data.

Image for Big Data Architecture
Big Data Architecture

The DataVisor Platform, from computation to data access and storage, is built on the latest big data infrastructure stack. Apache Spark, HDFS, Hadoop, Apache HBase and Elasticsearch are all being used to support the system in different capacities.

Image for Global Intelligence Network
Global Intelligence Network

The DataVisor Global Intelligence Network leverages deep learning technologies to provide real-time, comprehensive digital intelligence based on the industry’s widest set of digital data.

Architecture For Real Time Detection

The DataVisor UML Engine is designed to operate in batched and real-time modes. While they are built using the same algorithms, they are designed for different optimization goals. The batch system targets maximal coverage and accuracy, while the real-time system also addresses latency and throughput requirements.