Knowing which of your customers is most likely to churn gives you the opportunity to act before they make that critical decision.
The most effective way to predict likelihood to churn is with machine learning. With machine learning, you can constantly keep your list of customers up-to-date with churn scores based on the historical data of similar shoppers, and plug your likely-to-churn customers right back into your stack, no PhD required. With churn scores in your stack, you're primed to jump in, offer a discount, a helping hand, or some other offer to keep them on board.
Faraday makes predicting churn scores for your customers intuitive & easy, and delivering them to any channel in your stack a breeze.
With churn score predictions in HubSpot, you’ll give your team valuable insight to intervene before the customer makes that critical decision, exactly where and when they need it.
Follow the steps below to get your churn scores predictions into your HubSpot account.
In this guide, we'll show you how to:
- Organize your customer data into cohorts
- Describe predictive models for churn scores with outcomes
- Deploy churn scores predictions to HubSpot using Pipelines
You'll need the following cohorts available in your Faraday account:
- A cohort representing your customers — or create one first
- A cohort representing your churned customers — or create one first
Now you'll create the prediction objective(s) necessary to complete this use case with Faraday.
Outcomes use machine learning to predict whether or not people will exhibit a certain behavior.
Let's make an outcome for likelihood to churn.
- In the navigation sidebar, choose Outcomes.
- Click the New outcome button.
- Fill out the form:
- 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.
Now you'll configure the pipeline that deploys your predictions to hubspot.
- In the navigation sidebar, choose Pipelines.
- Click the New Pipeline button.
- Fill out the form:
- Click the Save pipeline button.
Your pipeline will start building in the background. You can proceed immediately with the next set of instructions.
- In the Deployment area, find the CSV module and click Add.
- Fill out the popup:
Choose the Identified option.
Choose Human friendly column headers.
- Click the Next button.
- Expand the Structure section of Advanced Settings
- Click the Finish button.
- Click the Test deployment button and confirm the results meet your expectations. 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.
With your pipeline deployed, it's time to plug your churn scores into HubSpot. Follow the steps below to see each HubSpot contact enriched with their churn score.
- In your Faraday pipeline, click the Download CSV button under the deployment to download your churn scores as a CSV.
- Navigate to HubSpot's import wizard via Contacts > Contacts > Import, select start an import on the left, and click next.
- Select file from your computer on the left, since you're uploading a contact list that you intend to reach out to, rather than the other option of an opt-out list. Click next.
- Select one file and click next.
- Select one object, as we're only handling contact data. Click next.
- Select contacts, and keep selections in "activities" blank. Click next.
- Select your CSV, and click next.
- In data mapping, ensure email is matched correctly, as it is used by HubSpot to match contacts in your CSV to their HubSpot record.
Under the "Import as" column, key rows to map to "Contact properties" are email and the percentile row outlined in step 9.
- In the final row, "fdy_outcome_propensity_percentile", ensure the "Import as" column selection is contact properties, click choose or create property, then create a new property.
- Under "Group", select contact information, as the property you're creating is for the contact card.
- Give the new property an appropriate label, such as "Churn score."
- Optionally give the new property a description,, such as "Faraday's churn score, or the percentile the customer is in based on their predicted likelihood to churn." Click next.
- Change "field type" to number under "values," as the percentile is numeric. Click next.
- Click create to finish creating the new HubSpot property for percentile, and ensure the new property is selected in the final row (step 9).
- Click next to move onto the final stage of the import, where you can name the import.
- If desired, tick the box for create a list from this import, which will save you a step when preparing to launch a campaign to target these likely-to-churn customers. Additionally, you can tick set these contacts as marketing contacts so that they are able to receive communication from you.
- Click finish import to wrap up. If you ticked the box to create a list in step 16, you can begin to plan a campaign to intervene just in time to keep your customers on board.
🔒 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.