In the first quarter of 2017, AppsFlyer’s Active Fraud Insights helped marketers detect and address over $30 million in fraud
AppsFlyer, the mobile attribution, and marketing analytics firm, introduced Active Fraud Insights 2.0, to detect and prevent the most advanced type of mobile fraud like DeviceID reset fraud, install hijacking, and click flooding among others.
Subsequently, AppsFlyer launched an initiative to regulate the AppsFlyer ecosystem with a review of its 2,500+ integrated ad networks to ensure they are minimizing fraudulent traffic being sent to marketers.
“Over the last two years, the scale and sophistication of mobile fraud has grown at an alarming rate,” said Oren Kaniel, CEO of AppsFlyer. “Thanks to AppsFlyer’s scale, we are in a unique position to detect and prevent mobile fraud faster and more consistently over time than anyone else in the industry.”
Part of the Active Fraud Suite, the Active Fraud Insights 2.0 leverages metadata from 98% of the world’s mobile devices, and proprietary technological advances in big data and machine learning to prevent mobile fraud.
Since Active Fraud Insights’ introduction in 2016, dozens of large marketing teams have been able to identify and stop offending campaigns, networks and even siteIDs before significant damage was done. In Q1, 2017, Active Fraud Insights helped marketers detect and address over $30 million in fraud. With the launch of the new upgrade, the platform offers visual clarity, dynamic filters, and proprietary insights to quickly identify fraud and take corrective measures.
Active Fraud Insights 2.0 is based on a proprietary mobile engagement database with over 500 billion mobile events measured every month. Active Fraud Insights 2.0 is the result of close collaboration between AppsFlyer’s scientists and advanced app marketers.
The latest Active Fraud Insights 2.0 includes:
Improved Visuals and Filters
New multi-select grouping filters by media source and siteID, now include Organic as a media source for a powerful benchmark data source. This allows marketers to quickly identify offending sub-publishers and take corrective measures.
Analyze data with Source Distribution Visual
This visual shows the percentage of sources with devices by DeviceRank™ rating. It could be sourced with high concentrations of new devices, devices with Limit Ad Tracking enabled, devices flagged as suspicious, or sources with low clean install rates. This new visual makes it easy to determine which sources warrant further investigation.
Click Flooding Detection
High click volume and low conversion rates suggest that source in question is over-reporting the clicks. Long click to install time (CTIT) times and high contributor rates, as well as high click volume with low click-to-install conversion rates, are all indicators of click flooding. The long CTIT times indicate that installs are being attributed to random clicks.
Install Hijacking Detection
Set a seconds timeframe to identify unreasonably short CTIT times. Install hijacking mobile malware insert clicks during the actual install. Unreasonably short CTIT times indicate hijacked installs. Whereas, a large number of installs with short CTIT indicate which sources are most compromised by install hijacking.
Install Fraud hiding behind Limited ad tracking
Online criminals try to avoid device-based fraud protection by enabling Limit Ad Tracking on their devices. High concentrations of Limit Ad Tracking in a given Geography(Geo), when correlated with low loyalty rates, helps detect install fraud.
Devise ID Reset Fraud Detection
Installs from new devices that are not yet rated by DeviceRank™ are rare. High concentrations of new devices indicate that the source has been compromised by DeviceID Reset Fraud.
Installs from Clean Devices
High concentrations of installs from devices ranked as clean indicate a strong, device-based fraud free source. These sources are a helpful benchmark when determining a source’s susceptibility to install fraud.
The company claims that this new setting marks a new standard for mobile fraud detection.
Read Also: AppsFlyer Just Raised $56 Million