Zoltar fortune teller booth on a boardwalk
Editorial

Google Analytics Brings Predictive Metrics to App + Web

3 minute read
Pierre DeBois avatar
Google Analytics introduced two predictive metrics to App + Web properties this July, which focus on purchase and churn probability.

Google Analytics launched its App + Web feature in 2019. True to its name, App + Web combines the dimensions and metrics of app and website data into one report view, to simplify reporting on customer behavior. I wrote about the details in this July 2019 post.

Since then, Google has been working to refine predictive capabilities to complement the insights from the App + Web report view. The addition of two new predictive metrics to App + Web properties this summer will help retailers and online businesses alike gain better insight into potential customer behavior. 

Bringing Churn Probability and Purchase Probability to App + Web

Understanding user behavior is a core service of analytics, but many tools are improving the calculations and visualizations that support that service. In this instance, predictive metrics identifies customer actions on your app or website that will likely lead to a purchase or a conversion activity, making it possible for marketers to better discover more people who are likely to convert at scale, e.g. a higher frequency of download, purchase or signups.

One predictive metric is Purchase Probability, which predicts the likelihood that users who have visited your app or site will purchase in the next seven days.

The second predictive metric is Churn Probability. It predicts how likely it is for recently active users to visit your app or site in the next seven days.

To use either of these metrics, you must use the Audience Builder, a user interface that presents preselected categories based on predictive probabilities. The categories are predictive audiences, the likeliest audience in a seven-day period. Four choices are available: purchasers, first-time purchasers, churning purchasers and churning users.

An analysis module appears in the App + Web reports to provide filters and selections to display the categories for a comparison. The Google Analytics blogpost on predictive probability gave an example of comparing campaigns by customer value, which can be useful for determining where to best shift spend of a remaining budget.

google analytics predictive module

Learning Opportunities

The benefit the metrics offer you is to guide resources to where engagement activity within your business is likely to happen. By knowing the people who are most likely to purchase and the people who might not return to an app or site through digital ads, your team can make faster decisions for deploying product offers and additional referrals.

Related Article: Less Is More: Dealing With 2020's Marketing Budget Challenges

Google's Predictive Metrics Roll Out

Google has begun rolling out the predictive metrics in Google Analytics properties with certain criteria, such as number of purchase events triggered and the proper installation of the App + Web property.

If you are installing App + Web for the first time, you should use your existing Analytics properties alongside the new App + Web property for a few days. This is to make sure it's operating properly without losing any data in the transition. I recommend this because any changes made to the Google Analytics script or settings is operational from the moment the website or app is live — you cannot retroactively change metrics if you need to correct a calculation or adjust a graph. This is just an aspect of how programming code operates combined with the nature of analytics to log pace actions. The safest approach is to overlap the change of script and document the changes in the annotation manager (I explain annotation in this post).

The arrival of these predictive metric should enhance the choices you make in Google Analytics and help you keep more of your customers satisfied.

About the author

Pierre DeBois

Pierre DeBois is the founder of Zimana, a small business digital analytics consultancy. He reviews data from web analytics and social media dashboard solutions, then provides recommendations and web development action that improves marketing strategy and business profitability.