In 2019 IAS surveyed over 900 digital advertising professionals, representing the buy and sell sides of our industry, to understand the trends, challenges, and opportunities that would shape 2019. We released our findings in the IAS Industry Pulse. One opportunity that ranked high with every segment of the study’s audience was artificial intelligence and machine learning. However, while agencies, brands, publishers, and technology platforms all agreed that these technologies represented a potential paradigm shift for digital advertising, the study also registered a consistent lack of clarity around just what that opportunity would look like.
One respondent, an account executive from a large ad tech provider, spelled out the problem succinctly. “Everyone wants to get in on AI/Machine learning,” wrote the executive, “but I find that it is very unclear what that even means. Can you truly have an opportunity that is 100% AI?” It’s a sentiment that’s been gaining steam over the last few years as AI and machine learning move from a technology on the theoretical horizon, to actionable tools widely available.
It’s one thing to understand how Alexa helps you prepare for the weather in the morning as you’re getting ready…it’s quite another to understand exactly what AI means for industries like digital advertising.
To bring some clarity to the discussion here are three ways that IAS uses machine learning and artificial intelligence right now, to improve the quality of media buying and selling.
1. Browser and device analysis – Machine learning allows us to identify invalid traffic sources by matching browser features to the user agent. While this type of determination is often mistakenly labeled deterministic, it would be impossible without employing machine learning methodologies to detect patterns within large data sets. Applied correctly, and powered by sufficient data, this method of detection can help to weed out entire bot networks.
2. Behavioral and network analysis – We use big data to distinguish real user behavior from bot behavior by looking at anomalies within site visitation patterns. Cohorts of bots tend to visit the same cluster of domains over and over because their behavior is automated. Detecting these patterns can allow us to surface bots based on their behavior. After all, most humans don’t visit the same sites, in the exact same order, multiple times per day. If these cohorts have only visited specific domains that can indicate a pocket of bot activity, we track these patterns and mark this traffic as fraudulent. Of course, machine learning techniques can also identify patterns in traffic that aren’t immediately obvious to human analysts.
IAS observes up to 10 billion impressions per day, the definition of big data. That scale allows us to build machine-learning models that can predict fraud which our peers with more limited scale and singular methodologies cannot. These models allow us to react quickly to new fraud innovations and be more resilient to bots that are trying to thwart our technology. Major consumer brands, like Uber and Amazon, are leveraging big data and machine learning to power major technological innovations, from driverless cars to drone delivery services, and we believe that marketers deserve access to the same predictive technologies to protect their digital investment.
3. AI for brand safety – At IAS we use artificial intelligence to automate our brand safety solution. Through machine learning informed by our extensive data science team, our solutions are able to continually improve their understanding of the digital landscape at scale, and can automatically assess and determine the appropriateness of new pages without requiring explicit programming to do so. We use AI to scale to our brand safety offerings, but we also apply a human lens to continuously audit and enhance our models so we are keeping up with the constantly evolving landscape of risky content.
Like our peers across the industry we see tremendous potential in AI and machine learning to continue transforming the way we do business. While it’s too soon to say we’ve identified all opportunities, it’s clear that these technologies could be applied to many facets of media quality. However, it’s important not to think of these technologies as far flung possibilities. As the examples above demonstrate, AI and machine learning are already a part of our business today.