How machine learning helps boost liquidity to achieve the best results

When you leverage machine learning, you can achieve what we refer to here at Meta as "liquidity"– a state of ad buying in which every dollar can flow to the most valuable impression for maximum efficiency. This is made possible when advertisers take their hands off the controls and allow the system to do the heavy lifting.

In some ways, achieving liquidity requires teams to become agnostic – letting the system do the work for you when it comes to budget, placement, audience and creative. If done right, users can expect increased liquidity to result in increased reach, lift or a combination of the two, as the system finds better opportunities to show the ad for the same cost. Combined with constant campaign spend, this often drives lower cost per outcome.

Dimensions of liquidity are interdependent

A campaign is more liquid when it has fewer constraints. That’s because limiting restrictions means the delivery system is able to select the best opportunities to serve ads from a broader pool, turning up valuable opportunities that would otherwise be excluded.

When you have clear goals and signals – such as pieces of your audience’s behavioural data – it’s easy to tell the system what you want and to set it free to find the optimal approach. But if your goals and signals are more opaque, you’ll need to put in some guardrails to guide the system and make sure that it doesn’t go too far off track.

While adding these constraints delivers more control, the trade-off is less liquidity. That can result in higher costs and lower efficiency, as reducing the pool of opportunities limits the system’s ability to find the most valuable ones.

How to create a liquid campaign setup

Meta offers various types of Ads Manager products to create campaign liquidity:

• Budget liquidity: Budget liquidity can be increased by removing restrictions on where the campaign’s budget can be spent, Advantage+ campaign budget allows advertisers to set their budget at the campaign level and let Meta’s AI automatically and intelligently distribute spend amongst ad sets to maximise campaign performance at scale.
• Placement liquidity: Placement liquidity is achieved by allowing Meta to determine which placement/impression combination will drive the best campaign results. Using 6+ placements or Advantage+ placements grants the ad auction optimal inputs to effectively calculate a campaign’s delivery distribution.
• Audience liquidity: Advertisers can increase audience liquidity by selecting a broad audience or by choosing Advantage+ detailed targeting, Advantage+ custom audience or Advantage+ lookalike to enable our systems to deliver ads beyond the original selected audience, if we think it is likely to improve performance.
• Creative liquidity: Creative liquidity is increased by providing multiple creative components, such as images and headlines, and allowing the ad auction to determine the most efficient combination. Advertisers can explore Advantage+ creative solutions.

Machine learning-driven systems save time and effort when setting up campaigns, help maximise liquidity for the most efficient buy and uncover fresh insights.

For any questions, contact Meta Support Pros, our dedicated support team for government, political and charity organisations.