Did you know that you have the power to predict the future using your past data? GA4’s predictive analytics can help you do just that. Read on to find out how you can anticipate future trends and stay ahead of the curve!
What are Predictive Metrics?
GA4’s predictive metrics are calculated using machine learning algorithms to predict future user behaviour based on historical data. They use algorithms to identify patterns and trends, providing valuable insights into your users’ potential next steps.
At the minute, GA4 offers three predictive metrics:
- Purchase Probability – Predicts the likelihood that a user will make a purchase within the next 7 days
- Churn Probability – Predicts the likelihood that a user who was active in the last 7 days will not be active in the next 7 days
- Revenue Prediction – Predicts the revenue expected from purchases within the next 28 days from users who were active in the last 28 days
These metrics are automatically generated by GA4.
How do Predictive Metrics Work?
GA4’s machine learning models analyse various user interactions, including:
- Events: Actions taken by users on your website, for example, page views, button clicks, form submissions.
- User properties: Attributes of your users, for example, demographics, location, device.
- E-commerce data: Purchase history, product views, and other related information.
By identifying patterns in this data, the models can predict the likelihood of future events.
Prerequisites for Predictive Metrics
To train the machine learning algorithms successfully, certain requirements must be met:
- A minimum number of examples: There must be a sufficient number of positive and negative examples of both purchasers and users who churned. Within the last 28 days and over a seven day period, at least 1000 returning users must have triggered the purchase or churn predictive condition, and at least 1000 returning users must not.
- Model quality: The model’s quality and accuracy must be consistent over a period of time
- Ecommerce data: Your property must be sending the purchase and in_app_purchase events. When you collect the purchase event, you need to also collect the value and currency parameters for that event.
If these requirements are not met, your predictive metrics will stop updating.
Predictive Audiences
Predictive metrics can be used to create predictive audiences, which allow you to target users with specific behaviours or potential value.
There are five pre-built predictive audiences:
- Likely 7-day churning purchasers: Purchasing users who are not likely to visit your site in the next 7 days
- Likely 7-day churning users: Users who are not likely to visit your site in the next 7 days
- Likely 7-day purchasers: Users who are likely to make a purchase in the next 7 days
- Likely first-time 7-day purchasers: Users who are likely to make their first purchase in the next 7 days
- Predicted 28-day top spenders: Users who are predicted to generate the most revenue in the next 28 days
This segmentation allows marketers to target different audiences more effectively.
Use Cases
Predictive metrics can be leveraged a number of ways:
Reducing churn: Once users with a high probability of churning have been identified, you can implement retention strategies such as sending personalised emails and offering special discounts to re-engage these users
Targeting high-value users: Identify users who have a high likelihood of of purchasing and tailor your marketing campaigns to encourage conversions through targeted adverts and promotions
Optimising marketing budget: By focusing on users who are most likely to generate high revenue, you can allocate your marketing budget more effectively
GA4’s predictive metrics offer a powerful way to anticipate future user behaviour and make data-driven decisions. Using these insights, you can optimise your marketing strategies, improve customer retention, and drive revenue growth.
Prefer Video? Watch on Youtube
For more on GA4, check out our 12 Simple Steps to Exclude Internal Traffic from GA4. If you have any questions or there’s anything else we can help with on GA4, please leave a comment below, or contact us at [email protected]. You can also follow us on @GlowMetrics or subscribe to our newsletter for more tips and news within the world of Digital Analytics and Marketing.
Don’t forget you can also sign up for a free account on our Resource Hub to access a wealth of valuable resources, including exclusive Digital Analytics and Digital Marketing how-to videos and insights across GA4, SEO, PPC and more.
Posted by
Hannah Magorrian
Hannah is a Digital Analytics Executive at GlowMetrics, working on creating data dashboards and assisting on wider analytics work across Google Analytics and Data Studio.
Read more from Hannah MagorrianBrowse by Category
- Social Media
- SEM
- SEO
- Google Ads
Digital Marketing
- Google Analytics
- Google Tag Manager
- Google Opimize
Digital Analytics
Optimise your website and marketing campaign performance with Ireland’s leading digital analytics agency
Sign up to our newsletterEnjoyed reading this article? Find more like it below…
Posted by
Nicola Russell
Feb 15th 2019
Digital Analytics Insights
4 min read
It’s Time to Check your Google Analytics for Amazon Bot Spam
UPDATE: As of 4th February 2020, the 'Network Domain' and 'Service Provider' dimensions in Google Analytics have been marked as 'no longer supported' and are returning (not set) values -...
Posted by
Conor Ross
Oct 19th 2020
Digital Analytics Insights
4 min read
Connecting Google Surveys to Data Studio
Google Surveys is one of the most recent additions to the lineup of products available within the Google Marketing Platform, allowing you to easily create and publish online surveys, either...
Posted by
Michael Wilson
Jan 8th 2019
Digital Analytics Insights
3 min read
Calculated Fields in Looker Studio – How to Use Text Functions
Have you ever set up a report in Looker Studio and realised your data isn’t as clean as you’d like it to be? Maybe you’ve used inconsistent naming conventions in...
Leave a Reply