Changing algorithms, assigned quality scores and machine learning models all play their part in determining which ads Facebook decides to show to which people. It can result in a lot of wasted spend and begs the question,”what does Facebook want?”
This recent blog post by Facebook is a good place to start to improve your advertising performance without wasting your budget. It explains that there are two main factors that determine which ads are shown to which users, these are:
- Audience targeting – set by the advertiser in the self-serve tools. Audiences are created based on categories such as age and gender, as well as actions indicating interest such as liking a Facebook Page or clicking on an ad. Advertisers can also use information they have about their audience, like a list of emails or people who’ve visited their website, to build a custom audience or a lookalike audience.
- Ad auction – Facebook selects the top ads to show to users based on ads with the highest total value score – a combination of advertiser value and ad quality. They find advertiser value by multiplying an ad’s bid by the estimated action rate. This is an estimate of how likely a particular person is to take the advertiser’s desired action, like visiting the advertiser’s website or installing their app. They then add the ad quality score, which determines the overall quality of the ad. Note: this serves the same purpose as Google’s ‘Quality Score’ rating.
They use machine learning to inform this process, explained in this diagram below:
Machine learning is used by Facebook to generate the estimated action rate and the ad quality score used in the total value equation.
To find the estimated action rate, machine learning models predict a person’s likelihood of taking the advertiser’s desired action, based on the business objective the advertiser sets for their ad, such as brand awareness, submit a form or purchasing a product. Their models consider that person’s behaviour on and off Facebook, as well as other factors, such as the content of the ad, the time of day, and interactions between people and ads.
Over time, as more people view the ad, their models get better at predicting the estimated action rate and ad quality.
Looking to make your Facebook advertising strategy pay off?
Here are three essential tips to make sure your campaigns are optimised for success.
- Make sure you have the right objectives set up that are working towards your desired business outcome – then use the most relevant ad formats to deliver this.
- Make sure any creative you use is fit for platform i.e. don’t just re-purpose your TVC or the same static image, create multiple formats in multiple sizes for each platform (Facebook and Instagram) and for each ad placement.
- Although the opportunity is there to go very granular and niche with your targeting, we recommend targeting a sizeable audience and allowing the algorithm sufficient room to do the job.
Read the full article here.