Need help with bigquery-ml-templates?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

144 Stars 32 Forks Apache License 2.0 21 Commits 0 Opened issues


BigQuery ML SQL templates for common marketing use cases

Services available


Need anything else?

Contributors list



The repository contains BigQuery ML templates for common marketing machine learning use cases. The templates use synthetic data, which was generated as per below use case and schema. * Customer is a B2B office supplier: OS Inc * OS Inc's customers are businesses whose information is stored in CRM in Account object * End users of these businesses login to OS's ecommerce website to order supplies; End user information (demographics, etc) is stored in the User object in CRM * Website activity of each user is tracked in GA360

Though these templates are based on a fictitious B2B company, the modeling techniques and methods apply equally to a B2C scenario as well.

Here are the three use cases: * Customer Segmentation: the practice of dividing a customer base into groups of individuals that are similar in specific ways relevant to marketing, such as age, gender, interests and spending habits. Segmentation allows marketers to better customize their marketing efforts to various audience groups. * Customer Lifetime Value (LTV) prediction: LTV is an important metric used by businesses to measure the total revenue that they can reasonably expect from a customer. It is used by these organisations to identify and prioritize significant customer segments that would be most valuable to the company. * Conversion/Purchase prediction: predict if a user “converts” or "purchases", which in this case is defined as someone signing-up for a membership program that the company offers. Membership has a cost but provides additional benefits e.g., free shipping. It is in the company's interest if many users sign up for this membership as it helps streamline their operations and also helps with recurring revenue.

For more info follow the link : Documentation


We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.