Transaction Fraud

As digital banking, fintech, and social commerce businesses flourish, so do fraudsters and their sophisticated attacks. Gone are the days where a single attacker uses a single stolen credit card to make a quick score. Financial fraud has become a professional enterprise, with a complete ecosystem of stolen credit cards, personally-identifiable information, knowledge-based authentication scripts, and more. DataVisor’s Unsupervised Machine Learning Engine can detect suspicious connections between accounts and events, allowing it to stop transaction fraud in real time.

Request Trial

How Attackers Hide Fraudulent Transactions

IP Obfuscation

Proxies, VPNs, and cloud-hosting services allow attackers to evade IP or location blacklists and digital-fingerprint solutions.

Disposable Emails

Attackers use mass registration techniques to create armies of emails to test stolen credit card information before attempting to purchase their primary targets.

Device Obfuscation

Fraudsters utilize mobile device flashing and virtual machines to appear as if they are registering from many different devices.

Account Incubation

Fraudsters age fake accounts for long periods of time while simulating realistic user activity to evade detection when they launch their primary attack.

Why Unsupervised Machine Learning for Detecting Fraudulent Transactions?

Modern fraudsters have learned to evade advanced fraud detection solutions that rely on supervised machine learning or rules engines by carefully probing their targets before attacking and continuously changing their techniques. Powered by the latest big data technologies, DataVisor’s Unsupervised Machine Learning Engine analyzes all accounts and events simultaneously to uncover highly correlated, suspicious clusters of fraudulent activities. When viewed in the full context of all accounts and events, transactions that are not suspicious in isolation stick out like a sore thumb. Even better, DataVisor’s unsupervised approach doesn’t require training data or labels to detect new attack techniques, drastically reducing the response time to these attacks.

Real-Time Detection

Stop fraudulent transactions before they are approved by uncovering the suspicious connections between transactions and accounts.

Unknown Threat Protection

Detect new and evolving attacks without waiting for training data or labels by analyzing the connections among all accounts and transactions.

Accuracy and Coverage

Increase the number of fraudulent transactions detected while at the same time reducing the number of false positives for good customers.

Learn More About How DataVisor Stops Transaction Fraud

CASE STUDY

Top Financial Institution Uses DataVisor UML Solution to Fight Fraudulent Transactions

Read Case Study

DATA SHEET

Learn about how DataVisor Protects Financial Institutions from Fraudulent Transactions and Account Openings

Download Data Sheet

CASE STUDY

How DataVisor Uses UML to Stop Fraudulent In-App Purchases at a Top Gaming Company

read case study

The DataVisor Detection Solution

Unsupervised Machine Learning Engine

Predict new, unknown threats without labels or training data by analyzing hundreds of millions of accounts and events simultaneously using the industry’s most advanced unsupervised learning technology.

Supervised Machine Learning Engine

Use industry leading supervised machine learning algorithms to augment the unsupervised machine learning detection with client-provided labels.

Automated Rules Engine

Generate and deprecate rules automatically, lowering maintenance costs and improving results explainability.

DataVisor Global Intelligence Network

Aggregate and analyze the industry’s broadest array of digital fingerprints and signals from billions of users across a variety of industries.

Account linkage view to discover hidden links among malicious accounts

Learn More

What’s Happening With Transaction Fraud

BLOG POST

The Changing Tide of Financial Fraud

Increased adoption of the EMV standard for credit card purchases is bringing about dramatic changes to financial fraud. Likely we will see a reduction in the amount of “brick and mortar” financial fraud transactions. But unfortunately it is going to result in a dramatic increase in the amount of online fraud as fraudsters change their focus to places that do not require the credit card to be physically present.

Read Blog

BLOG POST

Mobile Fraud Gone in a (Device) Flash

Device fingerprinting, i.e., collecting information from a device for the purposes of identification, is one of the main techniques used by online services for mobile fraud detection. The goal is to recognize “bad” devices used by fraudsters, such that they can be identified even when other attributes (such as user names or IP addresses) change.

Read Blog

BLOG POST

Virtual Goods, Real Fraud | Virtual Currency Fraud, Currency Arbitrage

The recent announcement from Activision Blizzard to acquire King Digital Entertainment, maker of the hit game Candy Crush, for a staggering $5.9 billion certainly turned some heads. Is there really that much money in the mobile gaming industry? In a word, yes, but it’s not just the game makers who look to profit.

Read Blog

Read DataVisor’s Latest Posts

Go To The Blog

Getting Started

Want to get started and find out how DataVisor can help find malicious accounts hiding inside your online service? Request a security assessment today!

Request Trial