The Video AdTech industry is currently facing a major adversary: fraud. AdTech fraud can come in many forms: bots, duplicate requests from the same user or IP, duplicate impressions … and the list goes on. Having an accurate assessment of who is actually watching your advertisement is incredibly important in mobile and video advertising to all sides of the ecosystem.
Advertisers and ad networks put in specific content, expecting high value and quality traffic from the users who watch the video in return for their investment. On the other side, publishers are looking for a reliable stream of revenue based on quality results and happy advertisers. This is only possible to determine if all parties are getting accurate feedback on valid traffic.
There have been several attempts at solving this problem, but often the solution only goes so far. For instance, there are platforms that report fraud, but do nothing to prevent it. Additionally, there are many programs that target some but not all types of fraud.
What then is the solution? Cydersoft, a provider of products and solutions for the mobile advertising industry, has come up with VideMob, an anti-fraud solution that harnesses the power of machine-learning to detect and prevent fraudulent traffic.
VideMob claims that what makes it unique is that existing Data Management Platform-only systems can usually detect fraud only at the request level, and they use predefined black/white lists which are not a real-time mechanism. VideMob uses real-time monitoring in order to detect abnormal user behavior using dynamic events. According to the company, the added benefit of real-time monitoring can significantly reduce the impact of fraud.
In VideMob’s pre-launch monitoring of customers’ traffic, the company stated that they found a 46% fraud and invalid traffic rate, accounting for nearly half of all mobile video advertising traffic. Of the fraud that VideMob detected over this period, 73.9% was reportedly blocked in real time at the request level, mainly comprised of non-human traffic, and 26.1% was detected from the full workflow including the impression level.
“One of the toughest struggles in video advertising is fraud, which affects both publishers and advertisers,” said Semion Rotshtein, CEO of Cydersoft. “With our real-time built-in anti-fraud solution, analyzing more than five billion daily requests with up to 1.5M QPS, we are cleaning up the industry, and providing both parties with a solution to maximize their investments.”
While the issue of fraud is far from solved, VideMob is working towards a future in adtech where fraud will be a much smaller and more manageable problem. Whether it’s real-time monitoring or the use of machine learning algorithms, VideMob presents interesting ways of tackling fraud.