Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML

Опубликовано 14 апреля 2021, 15:00

Notebook here → goo.gle/2QllRpS
More smart analytic reference patterns → goo.gle/2OJcek7

Learn how you can build a churn prediction solution on Google Analytics 4 (GA4) data using BigQuery ML.

With so many apps and games out there, gaming and app developers face high rates of user churn. Developers can take steps to motivate certain users to return, but to do so, the first step is building a machine learning solution to identify the propensity of any specific user churning or returning.

This is a step-by-step video that explores the churn prediction pattern in this environment and helps walk you through the entire process of building such a system in your organization.

You will learn how to:
- Export your GA4 data to BigQuery
- Prepare the training data using demographic and behavioral attributes
- Train propensity models using BigQuery ML
- Evaluate BigQuery ML models
- Make predictions using the BigQuery ML models
- Implement model insights in practical implementations

product: BigQuery ML, Google Analytics 4; fullname: Polong Lin, Minhaz Kazi;