Promotion Abuse 2018-05-11T16:05:21+00:00

Promotion Abuse

Promotions are valuable marketing tools, but they are highly susceptible to abuse. Because they are often one-off and unique, there is generally no historical data from which to create training data or labels. This means supervised machine learning models are ineffective, forcing companies to rely on simple rules and manually monitoring the promotion. DataVisor’s Unsupervised Machine Learning Engine is uniquely capable of detecting large-scale, coordinated promotion abuse because it analyzes all accounts and events at once. This allows it to uncover the hidden connections between accounts without training data or labels, and detect entire attack rings even if each member of the ring doesn’t look suspicious in isolation.

How Attackers Abuse Promotions Undetected

Location options red v0

IP Obfuscation

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

Location options red v0

Location Spoofing

Cybercriminals use software to fake their GPS location and take advantage of location-specific promotions.

smartphone options red v0

Device Obfuscation

Fraudsters utilize mobile device flashing, virtual machines and scripts to appear as though they are using different devices.

Mass Registration red v0

Multi-Account Attacks

Sophisticated attackers evade detection by accruing promotional credits or currency on one account and cashing out on another.

How UML Fights Promotion Abuse

DataVisor’s Unsupervised Machine Learning Engine is uniquely effective at detecting promotion abuse because it analyzes the hidden connections between all events and accounts in real time. This allows it to detect entire rings of attackers without training data or labels, even if each ring member doesn’t look suspicious in isolation. In addition, because these hidden connections are often detected at account creation, DataVisor can stop the attackers before they strike.

Labels - Blue - V1

No Labels or Training Data

Detect new and continually evolving attacks faster, without waiting for training data or labels.

Target - Blue - v0

Accuracy and Coverage

Analyze hidden connections between accounts to detect more attacks while lowering false positives.

Alert - Blue - v0

Early Detection

Detect malicious accounts at account registration, before they can abuse promotions.

Learn How DataVisor Fights Promotion Abuse

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.

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.

What’s Happening with Promotion Abuse

Ready to enhance your detection with unsupervised machine learning?