Introducing New GA4 Predictive Metrics

What are predictive metrics in Google Analytics 4?

Google Analytics automatically and riches your data by bringing Google machine learning expertise and predict the future behaviour of your users. With predictive metrics, you can learn more about your customers just by collecting structured event data.

Currently three predictive metrics are available for use in Analytics purchase probability and revenue prediction metrics.

Nobody can read the future but based on past behaviour we can create a machine learning model that can predict what uses might do does Google Analytics predictive metrics built on machine learning anticipate your user’s behaviour.

What can you use predictive metrics for?

Analyse customer activity with predictive metrics - for example, you can use the user lifetime technique to identify which marketing campaign help you acquire users with the highest purchase probability with that information you might want to decide to reallocate more marketing budget towards that campaign knowing that you're investing in the future success.

Reach predictive audiences in Google Ads - in the past, if you wanted to target people likely to take a conversion you might target people who added to cart however using this approach as you might miss People who never selected an item but are still likely to make a purchase. predictive audiences automatically determine  which customer actions on your website might lead to a purchase help you find more people that are likely to convert at scale.

Audience triggers - when users match the definition of an audience you can trigger events and goals that can then be imported into Google ads and recorded as a conversion, If curating a high-quality audience is your goal for a campaign. 

How to set up a predictive audience 

Once your property is eligible for predictions, you can use suggested audience templates to create your own audiences with conditions based on those predictions.

1. On the left, click Configure > Audiences.

2. Click new audience.

3. To create the audience based on a suggested audience:

  • Under suggested audiences, click predictive.
  • Suggested predictive audiences that meet prediction-modelling prerequisites are labelled as ready to use. Click one of the templates that's ready to use.
  • Modify the template to your needs using the audience builder.

4. To create a custom audience with conditions based on predictive metrics:

To edit a predictive condition as you create or edit an audience, choose one of the configuration options:

  • Most likely… (includes the top N% of users)
  • Least likely… (includes the bottom N% of users)
  • Custom (enter a percentage range or use the sliders to the right to select a range)

If you're using a custom range, the sliders let you see how many users are included and the likelihood of those users to meet the predicted condition. With a larger range, you can see that more users are included, but that a greater portion of them are less likely to meet the condition.


Choose Below

Manage & Optimise Campaigns in our app or upgrade & manage your subscriptions in our admin portal

Use The APPmanage my account