**New Feature***Use Predictive Audiences in Analytics to predict Purchase and Churn Probability

With the advancements of Machine Learning and AI, technology can now help Marketers and Advertisers to predict the behavior and target users based on their future actions.

Google has recently announced a beta feature called predictive audiences, Google Analytics can analyze future data via machine learning and predict the future actions people may take. Currently this is a beta version and is available for App+Web property

What is a Predictive Audience?

As per Google

A predictive audience is an audience with at least one condition based on a predictive metric. For example, you could build an audience for ‘likely 7-day purchasers’ that includes users who are likely to make a purchase in the next 7 days.

What will it detect?

2 things:

(i) Purchase Probability, which predicts the likelihood that users who have visited your app or site will purchase in the next seven days.

(ii) Churn Probability, predicts how likely it is that recently active users will not visit your app or site in the next seven days.

How is it useful?

You can reach and target people who are most likely to purchase and retain people who are about to churn. These audiences are directly shared with Google Ads once created.

Use case

(i) In Re-targeting/Re-marketing  campaigns

(ii) In Re-engagement campaigns

How to create the Predictive audiences?

Below is how you can create the Predictive audiences, it is available for App +Web property

Following options are available:

(i) Likely 7 days Purchasers

(ii) Likely first time 7 day purchasers

(iii) Likely 7 day churning purchasers

(iv)Likely 7 days churning users

Create predictive audiences

Below is a step by step method 

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's 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.

What are the Prerequisites?

Below are the details as per Google:

1. A minimum number of positive and negative examples of purchasers or churned users. In order to be eligible it is required that 1,000 users triggered the relevant predictive condition and that 1,000 users did not.
2. Model quality must be sustained over a period of time to be eligible.

The metrics for each model will be generated by user, once time per day. If the model quality doesn’t meet the above, the predictions will become unavailable.

Thanks for reading!

Sarang Kinjavdekar