Designed for the Digital Era

The DataVisor Platform 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 approach works without ‘labeled’ input data to automatically detect new and previously unidentified fraud and abuse patterns.

Unsupervised Machine Learning Engine

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

Big Data Architecture

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

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.

How the Unsupervised Machine Learning Engine Works

Dynamic Feature Extraction

Generates comprehensive set of features to describe user accounts without prior history.

Correlation across user accounts

Identifies suspicious clusters of accounts that have strong similarity in the feature space.

Advanced Feature Engineering

Enhances initial detection results with digital signals for advanced feature engineering.

Augmenting Supervised Machine Learning

Outputs results to train supervised machine learning models to further boost detection.

Ranking and Categorization

Ranks detected accounts with confidence scores for quick decision making.

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 needs to meet latency and throughput requirements.

Learn More About Unsupervised Machine Learning


eBook: Keeping Up with Fraud in Digital Banking

Are you ready to tackle new forms of financial fraud attacks? Online banking and digital wallets have opened up a floodgate of new attack vectors for fraudsters to develop newer and never before seen threats that are fast evolving and massive in scale.

Read More »

eBook: Taming the AML Beast

This ebook discusses how financial institutions can address some of the shortcomings of existing AML alerting tools to detect the ever more sophisticated money laundering networks.

Read More »

Ready to enhance your detection with unsupervised machine learning?