The anatomy of mobile ad fraud: Soft Fraud
Soft Fraud is a latter kind of fraud, commonly found among "trusted video ad networks." One of the main markers of the possible presence of Soft Fraud is a significant increase in VTA (view through attribution). Scalarr considers this type of fraud a part of the New Face of Mobile Fraud category.
1. In 2018 Soft Fraud was responsible for 2,7% of all fraud cases.
2. Manipulation with install attribution (display/click) is the main feature of Soft Fraud.
3. Despite the fact that the share of Soft Fraud is one of the lowest among all types of fraud, it has a strong upward trend.
How Soft Fraud works
Soft Fraud comes out of publishers that are dragging a part of the advertiser's organic traffic to themselves, manipulating display/click attribution models:
1. For ad video networks, the advertiser generates two tracking links - for attribution of impressions (standard window of attribution - 1 day) and clicks (standard window of attribution - 7 days).
2. The publisher intentionally attaches a click-tracking link to both impressions and clicks, thereby increasing the attribution window for impressions from one day to one week.
3. A part of the organic installs goes to the publisher. Thus, they reduce the average CPI of their channel and increase the chances of growing budgets in the future.
How to deal with Soft Fraud
One of the indicators of Soft Fraud is an extremely high share of impression-attributions. However, it is quite difficult to identify which ones are soft fraud, and which ones are the real impressions through attribution. To detect this type of fraud it requires a detailed analysis using ML and Big Data techniques.
Read Scalarr’s Ultimate Guide to Mobile Fraud Types to understand more about dealing with Soft Fraud in all specific cases.
The general principle of “mixes” grounds on the conscious use of several various types of fraud to get over the known protection measures of fraud ...
Fraud is an adaptive crime, so it needs special methods of intelligent data analysis to detect and prevent it