Index Exchange Introduces Adaptive Timeout, Incorporating Machine Learning into Header Bidding

By STS News Desk On May 21, 2019

Index Exchange Introduces Adaptive Timeout, Incorporating Machine Learning into Header Bidding

New product makes publisher page speeds smarter by adapting to each user, creating more opportunities for bidders and revenue for publishers

Index Exchange, the world’s largest independent ad exchange, introduced Adaptive Timeout, an innovative product that will boost publisher revenue through advanced machine learning, while optimizing page speed. By measuring device and network conditions, the Adaptive Timeout feature leverages an algorithm that determines a custom, intelligent timeout for each individual user on each individual page view. This includes a time landscape, which is the time it takes from a bid request to a bid response for each participating bidder. By adaptively modifying the timeout, the feature ensures the maximum number of bids make it to the publisher, thereby increasing revenue, while improving user experience in each unique condition.

Previously, publishers have largely relied on imprecise, fixed-value timeouts for all users, which led to publishers missing opportunities while waiting for bid responses in latency-constrained environments. Static timeouts led to a trade-off, whereby publishers had to sacrifice user experience to wait longer for header bidding, or sacrifice revenue by setting aggressive timeouts. Adaptive Timeout introduces intelligence and machine learning into header bidding, allowing for an adaptive timeout that is tailored to the user’s device and network latency.

“Incorporating machine learning into header bidding is a natural evolution of the product line, and adaptive timeout is the first of many innovations we’ll be enhancing with this technology,” said Gabriel DeWitt, Vice President, Product at Index Exchange. “We’re happy we can bring this level of sophistication to our publisher partners, as they’ve been looking to leverage automation instead of internal tech resources to optimize their configurations.”

Adaptive Timeout is calculated using the device type, connection speed and an aggregation of the recent history of a particular user’s time landscape. Through the use of an adaptive machine learning algorithm, the outcome is overall improvement to page speed on fast devices with fast connections and more bids from the header reaching the publishers ad server, without any additional development.

“Our long-standing partnership with Index Exchange is a testament to the company’s continued commitment to innovation and maximizing publisher revenue,” said Jeremy Hlavacek, Head of Revenue, Watson Advertising. “This latest feature will ensure more bid responses are making it into our ad server, while improving user experience. It’s a huge opportunity for revenue growth.”

Adaptive Timeout will be followed by a number of other header bidding innovations planned to be released over the second half of 2019.