Meet the Next-Gen
Proactive Fraud Prevention Technology

Copyright © 2021 DataVisor Inc.

A large C2C marketplace improved operational efficiency by 20x

Try Proactive Fraud Solutions to Protect Your Organization


About DataVisor

DataVisor is the leading fraud and risk management platform powered by transformational AI technology. Using proprietary machine learning algorithms, DataVisor restores trust in digital commerce by enabling organizations to proactively detect and act on fast-evolving fraud patterns, and prevent future attacks before they happen. Combining advanced analytics and an intelligence network of more than 4B global user accounts, DataVisor protects against financial losses and reputational damage across a variety of industries, including financial services, insurance, marketplaces, ecommerce, and internet platforms.


Why Is DataVisor’s Machine Learning Unique?

Detect New Attacks without Labels

UML does not require labels or training data to get started. This helps enterprises enter new markets without concern for fraud, and enables early detection and adaptive responses to fast-changing attack patterns. The UML models are self-adapting and therefore do not require constant re-tuning to maintain exceptional performance.

Handle Imperfect Data and New Values

Unlike traditional solutions that only analyze selected values from historical data, DataVisor’s UML analyzes all values, including high-cardinality categorical features and even new values from digital signals. UML is robust with respect to data quality issues, including partially missing data and data value format changes, helping enterprises unleash the full power of data.

Multi-Subspace Clustering and Graph Analysis

Clustering analysis produces suspicious groups of accounts that are highly similar or correlated. It consolidates the results by graph analysis to link clusters that share similar accounts or strong features. The process enhances the detection of unknown fraud and attack rings. 

Ensemble Modeling with Supervised Learning

The output from the unsupervised models can serve as training data to automatically train a supervised learning model and detect additional fraud. The ensemble modeling outputs a set of detected individual bad accounts, which is then combined with the detected attack rings to maximize detection coverage and reduce false positives.


What Is Unsupervised Machine Learning?

Unsupervised machine learning (UML) is a broad category of machine learning techniques that don’t require labeled input data. Instead, UML techniques infer a function to describe the hidden structures of “unlabeled” input data points. Often used to discover patterns within large volumes of unlabeled data, UML is especially effective for discovering new and unknown patterns.

What Is Device Intelligence?

Device fingerprinting is a process of collecting unique identifying information from a digital device that’s used for identity validation, fraud prevention and digital advertising. DataVisor’s device intelligence solution protects against mobile and web attacks from emulators, botnets, hijacked devices, app cloners and more, while delivering accurate signals, device IDs and scores to boost detection.

Why Is DataVisor’s Device Intelligence Unique?

Detect Emulators, Botnets, Hijacked Devices and More

DataVisor’s device intelligence identifies sophisticated attack techniques such as emulators, botnets, rooted and hooked devices, app cloners and cloud phones — even when IMEA and IMEI are missing. It detects bad actors abusing the new Macbooks with M1 chips, and delivers a unique device ID for each device, no matter how fraudsters change device parameters.

DataVisor collects accurate and extensive intelligence from desktops and mobile devices (Android and iOS). It gathers 100+ data fields in real time, including device info, operating system, network, timestamp, languages, user agents and more, and protects customer privacy by not collecting PII data.

Collect 100+ Data Fields from Android, iOS and Web

Edge computing processes data locally and reduces traffic loads at scale to eliminate latency and improve speed. By computing data on local devices, it protects customer privacy, reduces the amount of data at risk and minimizes investment in infrastructure.

Protect data and SDK with whitebox encryption and digital signature. Protect data from being hijacked, tampered or analyzed offline. Use a unique encryption key per device to provide advanced security, even when a few devices are compromised.

Secure with Whitebox Encryption and Digital Signature

Edge Computing


What Is Feature Engineering? 

Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques. High-quality features are important for fraud detection, because a machine learning model is only as good as the data and features it is fed. Today, data scientists spend 70% of their time on data cleaning and feature engineering. DataVisor makes the feature engineering process a lot easier by offering an advanced and automated Feature Platform.

Why Is DataVisor’s Feature Platform Unique? 

Out-of-the-Box Feature Packages for Fraud Use Cases

DataVisor’s Feature Platform provides pre-built feature packages that are optimized for specific fraud types, including application fraud, ATO, transaction fraud and other scenarios. Extensive out-of-the-box features based on DataVisor’s domain expertise reduce time spent manually building features from scratch.

Deep learning helps detect script-generated content, disposable email services, anonymous proxies, suspicious IP usage and more. Gather intelligence from DataVisor’s consortium database to provide unique signals such as entity ages, geo-usage profiling and blacklists.

Deep Learning Features and the Global Intelligence Network

Backtesting on Historical Data and Rapid Deployment

High Scalability and Big Data Architecture

Easily backtest on extensive historical data to validate detection performance, with full flexibility to choose the data's timestamp and sample set. Results are returned within seconds; all the features are production-ready and can be deployed in minutes.

Handle years of data for large institutions and process massive amounts of data in real time — 10,000+ QPS with only 10-50 ms latency. To minimize computation costs, DataVisor builds features on top of features, so that each feature is computed only once.


What Is Knowledge Graph?

Knowledge Graph is a graph-based visualization solution that collects and aggregates information from millions of nodes and relationships to derive insights. DataVisor’s Knowledge Graph builds visualized intelligence from omnichannel data to empower contextual decisions. It helps fraud, risk and AML teams uncover new patterns and defeat large-scale fraud and money-laundering activities in real time.

Why Is DataVisor’s Knowledge Graph Unique?

Deep-Link Analysis on Any Entity

Smart Layout and One-Click Investigation

Knowledge Graph ingests omnichannel data to build and visualize multidimensional connections among various entities, including users, groups, money flows, IPs, emails, addresses and other attributes in real time. It uncovers hidden patterns and finds the most suspicious cases.

The smart layout displays critical connections based on each fraud scenario. It highlights fraudulent relationships in the network and supports one-click investigations that connect new entities with previously detected fraud rings, without the need for manual searches.

Dynamic Update on Blocklists and Allowlists

Complete Customization and Intuitive UI

DataVisor’s dynamic integration supports marking a group of bad users directly on the linkage graph and adding them to blacklists, as well as bulk marking good users to whitelists. This enables real-time decision-making and saves extra steps between investigation and action.

The operations team has full control to define strong and weak linkages and set volume and time windows. DataVisor supports configurable connection and network depth building, enabling investigators to expand multiple layers and get granular insights.


High Scalability, Real-Time Detection

DataVisor’s platform is built on the latest big data infrastructure and is extremely scalable. It enables users to manage big data volume with high QPS and only 10-50ms latency, to power real-time responses to emerging threats across hundreds of millions of accounts and events. The platform supports both real-time and batch processing, as well as cloud and on-prem deployment.

DataVisor is the world’s leading AI-powered Fraud and Risk Platform that delivers the best overall detection coverage in the industry. With an open SaaS platform that supports easy consolidation and enrichment of any data, DataVisor's solution scales infinitely, enabling organizations to act on fast-evolving fraud and money laundering activities as they happen in real time.

Unsupervised Machine Learning

Discover unknown fraud without labels

Device Intelligence

Detect attacks from mobile and web

Feature Platform

Derive intelligence from big data

Visualize linkages to make contextual decisions

Knowledge Graph