Instant BQML for Universal Analytics Properties
Launch an automated BigQuery machine learning model in minutes.
Fill in the fields below with details about your Google Cloud, BigQuery, and Google Analytics accounts. Upon completing all fields, click download to generate a customized JSON file. Upload the file to CRMint to automate your pipelines.
Take me to Instant BQML for GA4
1. Go to https://console.cloud.google.com
2. Select or create your project
3. Click "Cloud Shell" button 
You are now ready to copy-paste these commands into the Cloud Shell Terminal:
# Double check if a Cloud Project is selected.
[ "$GOOGLE_CLOUD_PROJECT" == "" ] && echo -n 'Input a Cloud Project ID: ' && read project_id && gcloud config set project "$project_id"
# Downgrade app-engine-python.
sudo apt-get install google-cloud-sdk-app-engine-python=359.0.0-0
# Install the command-line.
bash <(curl -Ls https://raw.githubusercontent.com/instant-bqml/crmint/instant-bqml/scripts/install.sh) instant-bqml
# Create a stage definition for your environment.
crmint stages create
# Re-run the setup in case new elements are needed.
crmint cloud setup
# Deploy the updated App Engine services.
crmint cloud deploy
Your CRMint application can run in the same project as your GA360 BigQuery Export or a seperate project. Depending on the Cloud Project architecture, Instant BQML will notify you of specific permission requirements and alter queries to account for your specific Cloud Project architecture.

Your Cloud Project ID is a customizable unique identifier for your cloud project. Learn more about finding your Cloud Project ID here.

BigQuery datasets are stored in regional or multi-regional locations. For a full list of BigQuery dataset locations, please visit this link.

The Google Analytics Account ID can be found within Admin > Account Settings.

The Google Analytics Property ID can be found within Admin > Property Settings.

The custom dimension join key can be either the GA Client ID (cookie ID) or a unique User ID. More details on how to extract the GA Client ID can be found here.

The custom dimension for propensity score gets populated via Data Import. Create a new Custom Dimension and ensure that this newly created custom dimension has the same scope as the Join Key Custom Dimension.

The Google Analytics Dataset ID is generated once a dataset is created.
Your Google Analytics Dataset ought to be a Custom Dataset, shared with your BigQuery Enabled View at least using Query Time Import where the Key is the GA Client ID or User ID custom dimension & the Imported Data is the custom dimension placeholder for the propensity score.
Google Analytics audiences can be published to Google Ads and DV360.

Predictions from the pipeline are output to Cloud Storage prior to Google Analytics Data Import. You must create the Cloud Storage bucket first in order to upload files to it during the pipeline. Click here to access your Cloud Storage browser.

Google Cloud's Service Account needs to be added with edit user permissions to the Google Analytics property.