Fraud Prevention

Remove fraudulent ad inventory with Admetrics Fraud Prevention

The prevalence of fraudulent players in today‘s ad environment is an awkward reality. Even trusted ad networks and premium publishers have significant amounts of their inventories delivered to fraudulent automated traffic and never actually seen by human consumers.

Admetrics Fraud Prevention can counter the problem by providing the necessary analytical insights to optimize display and video inventory towards non-fraudulent traffic.

What types of fraud techniques does Admetrics Fraud Prevention address?

Bot traffic

Botnets (or other automated agents) posing as humans that view or click on display or video ads.

iFrame stuffing

Stuffing ads or content into a tiny pixel, so that they count as served, but never have a chance to be actually viewed by a human consumer.

Ad farming

Also called ghost sites or pseudo sites, Ad Farms are fraudulent web properties that only exist to host a massive amount of ads without providing content targeted to a human audience.

Ad injection

An in-browser attack in which ads are forced onto a website, displacing the initial web page content or overlaying on top of existing content or ads.

Ad stacking

Multiple ads are placed on top of each other, with only the top ad actually in view.

How it works

Algorithmic fraud risk assessment

Using a wide range of probabilistic and deterministic signals, Admetrics Fraud Prevention employs a multi-layered detection approach to calculate a risk score for every impression. We call this the ARPA score.

ARPA is algorithmic fraud risk assessment via machine learning based on a wide range of probabilistic and deterministic signals.

The ARPA metric can then be used to optimize spend, for example to limit the exposure of a campaign to placements with an assigned risk under, say 65%.
Referrer & domain tracking

Admetrics analyzes and qualifies referrer data of domains and iFrames to assign the fraud risk on domain level.

Hidden ad detection

Admetrics identifies fraudulent deliveries through techniques like ad stacking, iFrame stuffing, pixel stuffing and ad farming.

Viewability tracking

Admetrics leverages viewability tracking as an indicator for fraudulent traffic, for example identifying clicks from impressions that are not viewable or finding other common patterns of fraudulent impressions.

Reputation databases

Admetrics maintains its own blacklists of compromised IPs or devices. Additionally, we use industry standard, real-time databases of compromised clients, IPs and notorious proxies.

Classification of botnet traffic

Admetrics analyzes and qualifies incoming traffic for signals that indicate fraudulent intent, including spoofed user agents and browsers, abnormal behaviour or traffic patterns.

Classification of automated traffic

Admetrics differentiates between ad fraud botnets and benign automatic traffic (regular spiders and crawlers that are not employed to manipulate ad media).


Putting the data to use

If you‘re not exporting the data for use in other systems, you can use Admetrics Dashboard to directly access fraud metrics on domain level.

The basic set comprises ARPA metrics like Share of fraudulent automated traffic, Share of non-fraudulent automated traffic, Share of high risk traffic and Spend at risk (total spend considering high risk and medium risk traffic).
Simple integration

Adding Fraud Prevention to your stack

Like all Admetrics solutions, Fraud Prevention works like a charm with other systems and vendors in proprietary technical ecosystems.

Possible applications are feed integrationsAPI integrations or real-time interfaces for use in the programmatic area, like pre-bid flagging towards non-fraudulent impressions.

Interested? Want to learn more?

Get in touch
Let's talk!
Shoot us an email to or fill out the form below. We'll be in touch soon.
Thank you.
We'll be in touch shortly.