IRIS.TV on Machine Learning Yields Personalized Video Streams
Article by Steve Ellwanger (November 8, 2016)
BOSTON – Akin to what Pandora has done with streaming music, IRIS.TV brings adapted machine learning to video viewing preferences. Its white-label solution, licensed to digital publishers, uses artificial intelligence to create a “personalized viewing experience for every viewer,” according to CEO and Co-Founder Field Garthwaite.
“We ingest the archive from a publisher, look at the content and meta data on the content, structure and classify it so that the content is more easily discoverable over time,” Garthwaite says in an interview with Beet.TV. “We match the right video to the right viewer in real time.”
This translates to several hundred million video views through the IRIS.TV Video Programming Platform each month. “Some of our customers alone have over a million videos,” says Garthwaite.
For the average publisher, about 80% of its audience “will actually leave before the first video ends,” according to Garthwaite. But the other 20% is there to watch as much as they can. “They will stick around and watch another video and basically, like science, IRIS is able to consistently drive another four to eight videos for those kind of super users we call them.”
The company believes that while the majority of video viewing has been on social media, companies and marketers experience poor unit economics and lose control of their audiences. Not surprisingly, Facebook and YouTube are some of the only video players IRIS does not work with.
“On a monthly basis for a typical customer, we’ll see a 70 percent increase in views,” says Garthwaite. “So if you’re doing 10 million views a month, you can expect that we’ll take you to 17. Which is really significant if you’re selling all that ad inventory.”
IRIS.TV recently launched Campaign Manager, which lets marketers serve branded campaigns to targeted audiences organically on premium publisher owned-and-operated destinations. Campaigns programmed by IRIS.TV are ad-blocker resistant and are served only to engaged users.