Impact of Invalid Traffic on Vendor Profitability

Invalid traffic (ad fraud) have not been discussed in the context of vendor profitability before. To do this, we have created a Net Present Value (NPV) framework that allows straightforward modeling of economic impact from Invalid Traffic filtering with outputs such as EBITDA and Present Value provided for 8 years ahead.

We’ve been able to prove using actual financial data from 7 major DSPs, that not only Invalid Traffic filtering has a significant impact on profitability, but can dramatically increase the valuation of the company, while making it more attractive for potential acquirers (or investors).

The basic premise is very simple. If 20% of all traffic is waste, and a trading platform (DSP) has less than 80% demand vs. all available supply, in theory the DSP could filter out 20% without losing any revenue. Instead a DSP taking such action creates the causes for three different kinds of benefits; direct financial gains, indirect financial gains, and other gains.

Direct Financial Gain

– Reduce IT overhead cost

Indirect Financial Gain

– Increase buyer trust
– Avoid penalties (from passing through invalid traffic)
– Avoid lawsuits later (for negligence)

Other Gains

– Have cleaner data for better optimization signals
– In case of being throttled, have more bandwidth for legit bids
– Data warehouse related energy savings

Acme DSP

To make the point clear without highlighting any individual company’s situation, we’ve created Acme DSP as an example company for analysis using the data from 7 DSPs and aggregating it in to one using a simple average.

For the purpose of the example (Acme DSP) we’ve assumed the following:

– There is a significant over supply of inventory available for ACME’s buyers
– In case filtering would result in over-demand, ACME could increase supply
– Roughly 35% of revenue goes to covering traffic related costs
– A daily incoming (from exchanges) bid volume of 50 billion (bids per day)
– For IT cost related to operating Nameless we’ve used average of 3 providers

 

In the actual calculator, which we will later make available through Nameles.org, these settings with many other inputs can be easily changed to accurately reflect the situation of any company.

The results are awe inspiring. In short summary, many currently struggling DSP companies could make their business profitable simply by using Nameles to filter otherwise hard to detect Invalid Traffic. 

As Acme DSP is not struggling, in the 8-year forecast below, we can evidence breaking even 1 year earlier and almost 50% increase in EBIT on the 8th year.

 

We decided to use NPV as the basis for our forecasting as it is widely used and accepted as a “gold standard” for valuation forecasting in corporate finance, investment banking, and other financially savvy practices. Based on the increase in EBIT, we can witness a dramatic change in the valuation of the company with at least single-digit multiple from the first year onwards and a 9x multiple increase by year 8.

Let’s just leave it at that.

Entropy and Invalid Traffic Detection

For the past 16 months we have worked on analyzing daily ad exchange bid logs with the goal of creating a “signals intelligence” scoring mechanism that could handle 200 billion bid events in a 24 hour cycle with minimal system requirements.

Today we are able to compute the entropy scores for roughly 2 billion rows per 24 hour window on a single regular Linux server with 48GB of memory using a plain vanilla SQL backend.

Nameless is the first ever significant open source contribution for countering ad fraud. It can be effectively adopted by any company and can be complimentary to any other detection method.

What is entropy?

Entropy method is widely used in a variety of prediction challenges, and especially useful with problems where there are many unknowns, such as is the case with the fast moving ad fraud eco-system. Most people have heard
about entropy in association with thermodynamics, and particularly the Second Law of Thermodynamics, and that is where the concept is coming from. But not everyone know that it was actually entropy method that Alan Turing used when he famously cracked the Nazi Enigma code helping Allies win the World War 2.

Central to the information age, entropy measurement is simply a measure of randomness (or lack order if you prefer it that way).

For example, the entropy of a line is very low.

On the other hand, if we split the same line in to pieces and disperse it, now we have much higher entropy in the system.

It has been shown by various applications, including NSA and other government mass-surveillance systems, that entropy measurement offers a superior method for unsupervised anomaly detection.

Using Entropy measurement to detect ad fraud

Our premise was very simple; randomness in traffic patterns would tell if a site or app had inventory quality issues. Let’s consider two extreme scenarios:

a) website gets all of its traffic from one IP address

b) website gets all of its visits from unique IP addresses

In the case-a entropy is as low as it can be. In the case-b entropy is as high as it can be.

Frankly speaking, if your business is at all dependent on ad inventory quality, the picture does not look too good. In this eco-system advertisers waste a large portion of their money, while legitimate publishers lose their revenues to fraud sites.

Rule based configuration

Nameles gives the owner of the system 100% control over the rule configuration aspect of the system. It can be configured in minutes to settings ranging from spray-and-pray to paranoid. I obviously just made those up, and there are no catchy names but it is really 100% configurable by the user in terms of finding the right balance that meets other business objectives.

Rule based approach allows system owners to easily share rule configurations in a form of a configuration file, if they would choose to do so. For situations where Nameles is deployed as a compliment to an existing detection system or stack, rule configuration allows aligning Nameles with weaknesses or strengths of the propriety system its being used to compliment.