Meta Logo

Driving optimization with machine learning

default alt
What is machine learning?

Machine learning helps show the right ad to the right audience by using predictive analytics and algorithms. It helps improve ad performance by shifting spend wherever the system is likely to achieve the best results based on your campaign goals. This is known as liquidity.

Optimize your campaign setup so your ads get smarter, faster

Each time an ad is shown, our ads delivery system learns more about the best people and places to show the ad. The more an ad is shown, the better the delivery system becomes at optimizing the ad's performance. The learning phase is the period when the delivery system still has a lot to learn about an ad set. During the learning phase, the delivery system is exploring the best way to deliver your ad set – so performance is less stable and cost per result is usually worse. The learning phase occurs when you create a new ad or ad set or make a significant edit to an existing one. By learning how machine learning powers your ads, you can feel confident you’re setting up your campaigns to achieve maximum results.

Here are some best practices to consider when setting up and managing your campaign:

  1. Avoid frequent editing: Each time you make an edit that is considered significant, the learning phase restarts. Avoiding frequent editing allows the system to learn and get out of the learning phase without reset as quickly as possible.
  2. Avoid having too many ad sets and high ad volume: High ad set volume is a leading contributor to ad sets not exiting the learning phase. If you run too many ad sets at once, each ad set delivers less often. We recommend only including images or videos that are distinct from each other. Run no more than five ads per ad set for optimal delivery.
  3. Find more customers with broad audiences: Using broad parameters in your audience targeting increases the size of your audience and gives the system flexibility to find people likely to take your desired action. This can lead to better results and help you uncover unexpected audience segments for future campaigns.
  4. Opt into Advantage Campaign Budget: Advantage Campaign Budget, previously known as Campaign Budget Optimization (CBO), automatically manages your budget across ad sets to drive the most results for the lowest cost. Instead of setting individual ad set budgets, you set one overarching campaign budget that has the flexibility to shift spend to the best performing ad sets.
  5. Expand your placements: Advantage+ placements, previously known as Automatic placements, allows the system to find the most cost-efficient options across Facebook, Instagram, Audience Network and Messenger. With more options, the system is able to determine in real time where ads will get the best results for the lowest cost.

The learning phase is necessary to help the delivery system best optimize ads, so you shouldn't try to avoid the learning phase completely. Testing new creative and marketing strategies is essential for improving your performance over time. To learn more about the Learning phase, significant edits and learning limited click here.