Image Source: Google Analytics Blog 

 

Google Analytics just announced that they are introducing new predictive analytics capabilities, a trend that is skyrocketing across the data science industry.

 

Google Analytics helps companies measure the actions people take across their digital properties. Predictive analytics solutions could help businesses map the various stages of the buyer journey, which would enable the adoption of suitable campaigns and lead to higher sales and customer retention.

 

By applying Google’s machine learning models, Analytics can assess the data and predict future actions people may take. 

 

Google Analytics took their machine learning capabilities one step further and introduced two new predictive metrics to App + Web properties. 

 

The first 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, Churn Probability, predicts how likely it is that recently active users will not visit an app or site in the next seven days. 

 

Analysts can then use the metrics to help drive growth for their business by reaching the people most likely to purchase and retaining the people who might not return to their app or site via Google Ads.

 

Using Predictive Analytics With Google Ads

 

Predictive analytics is already one of the most widely adopted intelligent automation technologies in the world, with more than 80% of major enterprises deploying smart analytics, according to Statista.

 

In business, predictive models exploit patterns found in historical and transactional data to identify risks and opportunities. Solutions became increasingly important as companies realized the importance of using the data they already collected to generate insights, but also to detect patterns that can lead to determining the best course of action to reach their business goals. 

 

The global predictive analytics market size is expected to be valued at $23.9 billion by 2025, registering a CAGR of 23.2%, according to a study conducted by Grand View Research. 

 

With the new update, Google Analytics will now suggest new predictive audiences that you can create in the Audience Builder. 

 

As defined by Google, a predictive audience is an audience with at least one condition based on a predictive metric. The availability of predictive audiences depends on the underlying predictive metrics being eligible for use by meeting all prerequisites. If you have exported modeled audiences to linked product accounts, those audiences will not accumulate new users once Analytics stops modeling.

 

For example, using Purchase Probability, Analytics could suggest the audience “Likely 7-day purchasers” which includes users who are most likely to purchase in the next seven days. Using Churn Probability would suggest the audience “Likely 7-day churning users” which includes active users who are not likely to visit your site or app in the next seven days.

 

How To Create a Predictive Audience

 

In the Audience Builder, you can select from a set of suggested predictive audiences.

 

In the past, if you wanted to reach people most likely to purchase, you’d probably build an audience of people who had added products to their shopping carts but didn’t purchase. 

 

Google states that, with this approach, you might miss reaching people who never selected an item but are likely to purchase in the future. Predictive audiences automatically determine which customer actions on your app or site might lead to a purchase—helping you find more people who are likely to convert at scale.

 

For example, let’s imagine you’re running a pet shop and you’re trying to boost your online sales this month. Analytics will now suggest an audience that includes everyone who is likely to purchase in the next seven days—on either your app or your site—and then you can reach them with a personalized message using Google Ads.

 

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

 

  1. Sign in to Analytics.
  2. Navigate to the relevant App + Web property.
  3. Click Audiences in the left pane.
  4. Click New audience.
  5. Under Suggested audiences, click Predictive.
  6. Suggested predictive audiences that meet prediction-modeling prerequisites are labeled as Ready to use. Click one of the templates that are ready.
  7. Modify the template to your needs using the audience builder. You cannot edit the predictive condition, but you can add additional non-predictive conditions.

 

Analyze Customer Activity With Predictive Metrics

 

In addition to building audiences, you can also use predictive metrics to analyze your data with the analysis module. For example, you can use the User Lifetime technique to identify which marketing campaign helped you acquire users with the highest Purchase Probability. With this information you may decide to reallocate more of your marketing budget towards that high potential campaign.

 

By using the user lifetime technique, you can see how your users behaved during their lifetime as a customer of your site or app. The user lifetime technique can help you find specific insights such as: 

  • The source/medium/campaign that drove users with the highest lifetime revenue, as compared to revenue only for the selected month.
  • The active campaigns that are acquiring users who are expected to be more valuable, with higher purchase probability and lower churn probability, as calculated by Google Analytics predictions models.
  • Unique user behavior insights, such as when your monthly active users last purchased a product from your site, or when they were last engaged with your app.

 

Google says that analysts will soon be able to use predictive metrics in the App + Web properties beta to build audiences and help you determine how to optimize your marketing budget. 

 

In the coming weeks these metrics will become available in properties that have purchase events implemented or are automatically measuring in-app purchases once certain thresholds are met.

 

About the author

Sebastian Stan

Sebastian is a journalist and digital strategist with years of experience in the news industry, social media, content creation and management, and digital analytics.



eBook: Understand Your Customers

Cognetik eBook: Guide to User Journey Analysis

 

Related Articles