Repeat purchasers in Google Cloud SQL (Postgres)

Why use predictions for repeat purchasers?

Knowing which of your customers is most likely to buy again is key to keeping your customers on board and engaged to drive revenue.

The most effective way to predict likelihood to buy again is with machine learning. With machine learning, you can ingest your customer lists, predict their likelihood to buy again based on the historical data of similar shoppers, and plug your highest-scoring customers right back into your stack, no PhD required. With your repeat purchasers in your stack, you're ready to kick off a campaign to bring them closer to their next purchase.

Faraday makes predicting repeat purchasers among your customers intuitive & easy, and delivering them to any channel in your stack a breeze.

With repeat purchaser predictions in Google Cloud SQL (Postgres), you'll give your team the ability to focus on the customers that are most likely to come back for more.

Follow the steps below to get your repeat purchasers predictions into your Google Cloud SQL (Postgres) account.


In this guide, we'll show you how to:

  • Organize your customer data into cohorts
  • Describe predictive models for repeat purchasers with outcomes
  • Deploy repeat purchasers predictions to Google Cloud SQL (Postgres) using Pipelines

Getting started with repeat purchasers in Google Cloud SQL (Postgres)

Make sure you have a Faraday account (signup is free!) and that it's not in test mode.

Requirements for this repeat purchasers recipe

You'll need the following cohorts available in your Faraday account:

Screenshot of the cohorts listing that includes Customers and Repeat purchasers You'll also need the following connections available in your Faraday account:

Screenshot of the connections listing that includes Google Cloud SQL (Postgres)

Building predictions for repeat purchasers in Google Cloud SQL (Postgres)

Now you'll create the prediction objective(s) necessary to complete this use case with Faraday.

Describe your repeat purchasers predictions with outcomes

Outcomes use machine learning to predict whether or not people will exhibit a certain behavior.

Creating an outcome for likelihood to buy again.

Let's make an outcome for likelihood to buy again.

  • In the navigation sidebar, choose Outcomes. Screenshot of the outcomes list
  • Click the New outcome button.
  • Fill out the form:
    • For Eligibility cohort, pick the cohort that best represents your customers.
    • For Attainment cohort, pick the cohort that best represents your repeat purchasers.
    • Leave Attrition cohort blank.
    • Skip over Trait blocking.
    • Enter a memorable name, like "Likelihood to buy again". Screenshot of the new outcome form, filled out
  • Click the Save outcome button.

Faraday will do some magic in the background, so you can proceed with the rest of the instructions. When your outcome is done building, you'll get an email, and you can review your outcome.

Using Pipelines to deploy predictions to your stack

Now you'll configure the pipeline that deploys your predictions to gcp_cloud_sql_postgres.

Create your pipeline for repeat purchasers in Google Cloud SQL (Postgres)

  • In the navigation sidebar, choose Pipelines. Screenshot of the pipelines list
  • Click the New Pipeline button.
  • Fill out the form:
    • For Payload, choose the following:
      • Outcome: Likelihood to buy again
    • For Population to include, choose the following:
      • A cohort representing your customers
    • For Population to exclude, choose the following:
      • A cohort representing your repeat purchasers
    • Enter a memorable name, like "Repeat purchasers in Google Cloud SQL (Postgres)". Screenshot of the new pipeline form, filled out
  • Click the Save pipeline button.

Your pipeline will start building in the background. You can proceed immediately with the next set of instructions.

Deploying your pipeline to Google Cloud SQL (Postgres)

Google Cloud SQL (Postgres)

  • In the Deployment area, find the Google Cloud SQL (Postgres) module and click Add. Screenshot of the ready pipeline with no targets yet
  • Fill out the popup:
    • Provide the specified parameters for Google Cloud SQL (Postgres).
    • Click Next.
    • Choose the Identified option.
  • Click the Next button. Screenshot of the new target form, filled out
  • Skip the "Advanced Settings" by clicking the Finish button.
  • Click the Finish button.
  • Click the Test deployment button and confirm the results meet your expectations. Screenshot of a target after hitting its test button the first time Faraday will finish building your pipeline in the background. When it's done, you'll get an email—return to the pipeline and click the Enable pipeline button to activate it.

How to use your repeat purchasers predictions in Google Cloud SQL (Postgres)

With your pipeline deployed, your repeat purchase scores are loaded into a CSV and ready to be plugged into your favorite marketing activation platform, where you can kick off a campaign to target the customers who are most likely to come back for more.

🔒 It's a best practice to permanently delete any file that contains personally identifiable information (PII) after use. Any deployment from Faraday that is unhashed contains PII, and should be deleted after uploading it to your destination for security purposes.