Fighting Ad Fraud with Artificial Intelligence
Advertising fraud, ad fraud for short, has become a major threat to the digital advertising industry. According to the Association of National Advertisers in the US, ad fraud will cost companies an estimated US$6.5 billion in 2017. A recent report by Juniper Research paints an even grimmer picture, estimating advertisers will lose US$19 billion to fraudulent activities next year. This figure, representing advertising on online and mobile devices, will continue to rise, reaching US$44 billion by 2022.
The industry has spent considerable resources looking for effective ways to mitigate the effects of ad fraud. I use mitigate deliberately because just as with cyber fraud or financial fraud, there is no way to totally eradicate the problem: you can only hope to stay one step ahead of the bad guys.
Most ad fraud countermeasures have centred on rule-based methods and these are effective ways to combat simple ad fraud activities. However, the ad fraud attempts are becoming more sophisticated and traditional countermeasures are inadequate today.
An AI-based approach
As ad fraud attempts become more sophisticated and difficult to detect, so must our fraud detection mechanisms evolve in tandem and the only way that this can be achieved is using artificial intelligence (AI).
An AI-based ad fraud detection system actually starts with a rule-based approach as the base but through self-learning, builds layers of defence that learn from each suspicious activity that it detects. An AI-based model also has the advantage of being able to view patterns on many more dimensions than a traditional system.
Traditional rule-based models typically analyzes activity on between one to three dimensions. An AI-based model analyzes over 80 dimensions at a time, enabling it to detect extremely sophisticated ad fraud patterns. With self-learning, AI-based models can evolve as ad fraud patterns evolve to evade traditional systems.
A Real World Study
To demonstrate the advantages of an AI-based approach, Appier examined data on its own network over four months from May to August this year involving over 4 billion campaign data points including ad clicks and app installs. What we found was that the AI-based fraud detection model was able to identify twice as many fraudulent transactions as the traditional rule-based model. The AI-based model also proved to be more cost-efficient for advertisers, yielding a 3.6 percent higher return on advertising spend (ROAS) than the traditional model.
The greatest advantage of AI though, was its ability to detect sophisticated ad fraud patterns not previously reported. On pattern that our AI system flagged is what we call “the chameleon”. This is where dishonest publishers disguise themselves as legitimate publishers at first, only to generate fraudulent installs at a later date.
Another suspicious activity detected by our AI is what we have termed “inventory burst”. With this pattern, a fraudulent publisher will generate an abnormally high inventory count in the absence of an appropriate level of in-app registration activity.
You can download the full report of Appier’s study here. Ad fraud is costing the industry billions of dollars and has become extremely difficult to detect. Traditional rule-based methods are limited in their ability to detect new and increasingly sophisticated ad fraud patterns. An AI-based approach with its ability to analyze multidimensional data and with self-learning is a better approach to fighting ad fraud.
WE ARE HERE TO HELP
YOU MIGHT ALSO LIKE
Medical science has always been data rich. For centuries, scientists have collected data through experiments, longitudinal studies, research and even day-to-day activities such as taking case notes after meeting with a patient. However, the COVID-19 pandemic has seriously altered the game. While even the biggest medical research programs have dealt with hundreds of thousands of cases, the pandemic affects billions of people. With so much data from many different sources flying in, artificial intelligence, or AI, is being used to help combat this virus. Using AI to Make Data-Driven Decisions Data scientists have been primarily focused on four key issues when trying to interpret page sets of data: volume, velocity, variety and veracity. These ‘four Vs’ are a significant challenge. With COVID-19, data is coming in from all over the world, at different times, from many sources and from systems with varying degrees of certification and accuracy. In December 2019, an artificial intelligence platform called BlueDot, which scans data from hundreds of sources, detected a cluster of pneumonia-like illnesses in Wuhan, China. Today, almost everyone knows this was ground zero for the coronavirus pandemic. Without BlueDot, it may have taken weeks longer for the world to become aware of
When I started Appier five years ago, artificial intelligence (AI) was not a hot topic. It’s hard to imagine that the first few business ideas were actually brainstormed in our dorm room in Harvard, and we will always remember the joy of the very first time that our customers trusted us and gave us our first order. In those first few years, we faced a lot of challenges, and we learned a lot, too. The first lessons we learned as entrepreneurs was to dream big and embrace failure. We keep this entrepreneurial spirit alive as our company grows, and we encourage our employees to develop their own entrepreneurial mindsets. When you’re not open to risks and failure, bold new ideas will never take off. Over the past 5 years, we were always thinking about how to make a real impact to human society and industry with AI when our products go on the market. We experienced eight pivots, from AI-based social games to the marketing and data intelligence platforms for enterprises that led to our initial success. We will never give up and we will always have the faith of continuously innovating. We have grown from a 4-person startup to
The global market of artificial intelligence (AI) continues to grow. According to IDC, at least 90 percent of new enterprise apps will embed AI by 2025. One of the reasons behind this trend is a growing awareness of the benefits of AI, together with the increasing accessibility of advanced AI capabilities, enabled by AI as a service (AIaaS). What Is AI as a Service? AI as a service is like any other out-of-the-box offering. It is artificial intelligence software being offered by a third-party provider to a client as a service, including a wide range of different AI-powered capabilities. These capabilities hosted by the third party sit in the cloud and are available to the end-users over the internet, making AI more accessible. Demand for AIaaS is growing as businesses increasingly see the value it is creating for competitors. Industry figures suggest that the global market of AI as a service will hit US$10.88 billion by 2023, up from US$1.13 billion in 2017. However, it could potentially be much higher as it becomes more available. What Are the Different Types of AIaaS? There are various types of AIaaS solutions. Which type you choose comes down to your business