Are you looking for ways to better understand and measure the likelihood of conversions on your website? Google Analytics 4’s Predictive Metrics is a powerful tool to help you do just that.
In this blog post, you will learn about what predictive metrics are and how they work in Google Analytics 4 (GA4). Get ready to learn more about how to unlock the power of machine-learning to boost conversion possibilities on your website!
What are Predictive Metrics?
Predictive Metrics in GA4 derive from machine-learning algorithms that help you measure the possibility of a conversion and the progress toward it. Google Analytics 4 uses predictive metrics to predict user behavior, providing you with the following data: Churn Probability, Purchase Probability, and Revenue Prediction.
Churn Probability is a metric that shows the probability of a user who was active on your website or app in the last 7 days, not being active in the next 7 days.
Meanwhile, Purchase Probability is the probability that a user who was active in the last 28 days will make a purchase within the next 7 days.
Lastly, Revenue Prediction represents the revenue that’s expected to be made in the next 28 days from the users who were active within the last 28 days on your website or app.
How Does It Work?
The machine learning algorithm takes into account several factors such as pageviews, time spent on page, types of content viewed, demographics, device used, and location to identify potential high-value customers.
Once the model is built, it uses the data collected to make predictions about the probability of a user converting. These predictions can be used to create personalized experiences for visitors, allowing you to maximize the value of each user’s visit.
Using predictive metrics in Google Analytics 4 gives you better insights into how customers interact with your website, helping you make more informed decisions and driving greater conversion rates.
Getting Started with Predictive Metrics
To get eligible for predictive metrics like ‘purchase probability’ and ‘churn probability,’ you must configure the purchase event and send it to the GA4 property.
A minimum number of 1000 positive and negative samples (purchasers and churned users) are required. This means at least 1000 users should have triggered the predictive condition to purchase, and 1000 users did not.
Model quality (regular traffic generating purchase events) must be sustained over a period of time, which is generally 28 days.
Each eligible model will generate predictive metrics for each active user once per day. In case any of the prerequisites are not met, or fall below the minimum threshold of users, then Google Analytics 4 will stop updating the predictive metrics, and it will be unavailable in Google Analytics.
You can check the status of each prediction provided by GA4 in the predictive section within ‘Suggested Audiences’ templates in the ‘Audience Builder’. If there is not sufficient data to use predictive modeling, an audience will be marked as ‘Not eligible to use’.
You can use predictive metrics in ‘Audience Builder’ while creating a custom audience. Using predictive metrics, you can create custom audiences such as:
- Users who are likely to purchase in the next 7 days.
- Users who are likely to make their first purchase in the next 7 days.
- Active users who are likely to not visit your website in the next 7 days.
- Purchasing users who are likely to not visit your website in the next 7 days.
You can also use predictive metrics in the ‘Analysis’ tab while creating User Lifetime reports.
To conclude, by taking advantage of Predictive Metrics in Google Analytics 4, you can gain valuable insights into user behavior and optimize your marketing efforts accordingly. With the data provided by these metrics, you can better understand which actions are more likely to lead to conversions, giving you the information you need to make informed decisions about your business strategy.