Transitioning to automated bidding models

Automated bidding models are designed to help you easily and effectively achieve your goals. These models take the guesswork and heavy lifting out of setting bids manually.

What are Criteo’s automated bidding models?

Also known as “Adaptive Optimization” and “Budget Optimization” models, these are Criteo’s most advanced way to improve your campaign performance.

Here are some of the features of using an automated bidding model:

  • Accurate budget spend: Accurately spend your allocated budget over a specified time-frame, while maximizing performance
  • Control and flexibility: Take full control of the bid strategy set-up and use an array of bid factor controls that give you flexibility to tailor bids to a user’s unique circumstances
  • Meet KPIs: Machine learning and advanced technical capabilities optimize your bids throughout the day to maximize conversions, revenue, or visits to meet your performance goals
  • Work smarter, not harder: Eliminate the need for manual adjustments and constant oversight. Improve time-efficiencies, consistency and accuracy by allowing our advanced AI capabilities to do the hard work and deliver more accurate results for you

How does it work?

If you’d like to get started using an automated bidding model, get in touch with your Criteo team. Once you’re using an automated bidding model, you can modify it from the Campaigns section.

Set a target for your Cost of Sale (COS) or Cost per Order (CPO). Performance is maximized by adjusting bid levels every hour. This means your campaign can run with more precision than through manual CPC management, bringing you closer to your targets.

Setting up automated bidding models

If you’ve previously been using a manual budget, you need to first accept the Terms & Conditions addendum in Management Center to get set up on an automated bidding model.

The addendum covers the dynamic update of bids to reach the relevant target (Cost of Sale or Cost per Order). Get in touch with your account team if you have trouble accessing the addendum.


Transition best practices

To ensure a smooth transition, we recommend you keep a campaign running for a week with a stable COS/CPO on the standard optimization model before switching to an automated bidding model.

Your starting target should be close to your current campaign’s COS/CPO, otherwise our algorithm might need several days to learn and find the right bid level for that target.

Automated bidding models rely on your campaign sales to calculate the perfect bid level. Accuracy, target stability, and performance improve with more sales volume. For the Criteo AI Engine to function properly, you’ll need to have an average of three daily post-click sales.


Managing performance

To maximize performance, we suggest merging campaigns that have similar targets. Smaller campaigns will typically take longer to reach stable performance.

For Criteo to calculate the optimal bid level for a given target, it is important to keep your input target stable. Changes of more than 20% should be avoided, as it can take up to one week for the engine to achieve a stable COS/CPO in line with the new target. We recommend limiting target changes to no more than every ten days.

You can always revise your target at any time in Management Center to influence the rate of spend. Alternatively, you can contact your account team to discuss steps to control the trend of the spend of your campaigns.


Evaluating performance

This new way of optimizing your campaign against a set target requires a slightly different approach to managing and evaluating your campaign performance.

Performance against the target should be measured and evaluated over a 7-day window for bigger campaigns which generate 20+ sales a day and over a 14-day window for smaller campaigns.

This is due to a combination of things, such as the engine’s response to valuable traffic and the time between a click and a resultant sale. You can be assured, however, that the engine is constantly working to achieve your target.

Automated bidding models adapt dynamically to external conditions but might not have enough insights about significant events affecting your traffic and sales such as Black Friday where the conversion rate jumps significantly. If you anticipate this kind of event, make sure to contact your account team to learn how to implement our Peak Mode strategy for your campaign.