Blog

How Adaptive Timeout™ Incorporates Adaptive Machine Learning

We’re excited to introduce a new feature for media owners: Adaptive Timeout™. Adaptive Timeout helps boost media owners’ revenue through advanced machine learning, while optimising page speed.

Today, all wrappers available to media owners use a fixed-value timeout. Most media owners use a single fixed timeout for all of their header bidding supply, regardless of factors such as device type or the consumer’s network conditions. This presents a significant opportunity for optimisation.

With Adaptive Timeout, media owners now have an adaptive machine learning feature that accounts for these variables. This feature helps increase the number of bid responses for all bidding adapters that media owners can evaluate, and increases revenue while improving the consumer experience. Static timeouts led to a trade-off, whereby media owners had to sacrifice the consumer experience to wait longer for header bidding, or sacrifice revenue by setting aggressive timeouts.

Why header bidding with adaptive machine learning matters

Across all media owners using the Index Exchange Wrapper, the average timeout for bidding adapters is around 15%. This led to media owners missing opportunities while they waited for bid responses in latency-constrained environments.

Because not all potential bids are evaluated due to timeouts, a media owner can lose out on many bids, including the highest bids from media buyers. We realised that by creating an adaptive machine learning algorithm that accounted for device type, geographical location, and network conditions, we could optimise the media owner’s wrapper timeouts.

How Adaptive Timeout works

Adaptive Timeout is based on an adaptive machine learning algorithm and optimises a media owner’s wrapper timeout for each individual consumer on each individual page view. This approach maximises a media owner’s revenue without any development work, while also enhancing the consumer experience.

Adaptive Timeout allows media owners access to an adaptive machine learning algorithm to adjust the wrapper timeout value as the consumer’s network conditions become faster or slower. It also considers other factors, such as the device type and the geographical location of the consumer. With all of these inputs, Adaptive Timeout can ensure an optimal time for header bidding and an optimal browsing experience for the consumer.

“Our long-standing partnership with Index Exchange is a testament to the company’s continued commitment to innovation and maximising publisher revenue. 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.”

Jeremy Hlavecek, head of revenue
Watson Advertising

To learn more about Adaptive Timeouts, head to our Knowledge Base or contact us.

Index Editor

Index Editor

This post was published by the Index Exchange editorial team.

Back to blog