Persona assignments in Poplar

Why use predictions for persona assignments?

Ah personalization, the holy grail of growth teams everywhere. Too bad it’s so difficult to do well.

The best way to personalize email is the simplest: organize your customers into personas, then produce straightforward variations of your email content for each persona. This way, you can have both copy and creative perfectly aligned with the interests of each persona so that your customers feel like you get them.

Faraday makes discovering your brand's bespoke personas intuitive & easy, and delivering them to any channel in your stack a breeze.

With persona assignment predictions in Poplar, you'll give your team the ability to personalize engagement to perfection through insights from AI-generated personas.

Follow the steps below to get your persona assignments predictions into your Poplar account.

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

  • Organize your customer data into cohorts
  • Describe prediction models for personas with persona sets
  • Deploy persona assignments predictions to Poplar using Pipelines

Getting started with persona assignments in Poplar

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

Requirements for this persona assignments recipe

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

Screenshot of the cohorts listing that includes Customers

Building predictions for persona assignments in Poplar

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

Getting started with Poplar personalization

Persona sets use machine learning to organize people into unique, coherent subgroups (called personas) that you can use to personalize your outreach.

Creating a persona set for your Customers

Let's make a persona set that organizes your customers into personas.

  • In the navigation sidebar, choose Persona sets. Screenshot of the persona sets list
  • Click the New persona set button.
  • Fill out the form:
    • For Choose a cohort, pick the cohort that best represents your customers.
    • Leave the advanced settings at their defaults.
    • Enter a memorable name, like "Customers". Screenshot of the new persona set form, filled out
  • Click the Save persona set button.

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

Screenshot of the persona sets listing that includes Customers

Using Pipelines to deploy predictions to your stack

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

Create your pipeline for persona assignments in Poplar

  • 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:
      • Persona set: Customers
    • For Population to include, choose the following:
      • A cohort representing your customers
    • Enter a memorable name, like "Persona assignments in Poplar". 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 Poplar


  • In the Deployment area, find the CSV module and click Add. Screenshot of the ready pipeline with no targets yet
  • Fill out the popup:
    • Choose the Identified option.

    • Choose Human friendly column headers.

  • Click the Next button. Screenshot of the new target form, filled out
  • Expand the Structure section of Advanced Settings
    • From the dropdown, select the poplar preset. Screenshot of the second page of the new target form, filled out
  • 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 persona assignments predictions in Poplar

With your pipeline deployed, it's time to plug your persona assignments into Poplar. Follow the steps below to create an audience in Poplar.

Creating a new audience in Poplar

  1. In your Faraday pipeline, click the Download CSV button under the deployment to download your persona assignments as a CSV.
  2. Since Poplar doesn't allow unique audience member tags or fields, you'll need to edit the CSV such that each CSV file includes only one persona.
  3. Navigate to Poplar's Audiences dashboard, then click new audience in the upper right.

Image of Poplar new audience creation

  1. Give your audience an appropriate name, unique to the one persona you split the CSV into, and optional description, then click create audience.
  2. In the view for your new audience, click upload CSV in the upper right.

Image of Poplar upload csv

  1. Select one of your persona-specific CSVs from step 2 in the file picker, and the page will load briefly.
  2. Map your CSV fields to Poplar fields. Most fields are likely to map automatically.

Image of Poplar field mapping

  1. As we already know that this CSV includes only the most persona assignments, we can safely select ignore this column for the two final columns indicating predictive scores.
  2. When finished, click continue to start the upload process.
  3. Once the upload is finished, you'll be presented with a confirmation screen indicating the total records imported. Click finish importing to finalize the import. You'll receieve an email from Poplar when your audience is ready, after which you can use it to launch campaigns to target only the best fits. Repeat this process for each persona-specific CSV you split the original deployment into in step 2.

🔒 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.