liveBook · Manning

Persuadable

As explained in Causal AI

A persuadable is a person who would experience the favorable outcome if a promotion or treatment were applied but the unfavorable outcome otherwise.

When a promotion has a cost, the practical question is not who will respond, but who will respond favorably because of the intervention. A persuadable is a person who would experience the favorable outcome if the promotion or treatment were applied, but the unfavorable outcome otherwise. section 8.3.3

Counterfactual segmentation contrasts persuadables with three other response types:

  • Lost causes experience the unfavorable outcome with or without the promotion. section 8.3.3
  • Sure things experience the favorable outcome with or without the promotion. section 8.3.3
  • Sleeping dogs would experience the favorable outcome without the promotion but the unfavorable outcome after receiving it. section 8.3.3

Churn-prevention promotion

For a subscriber, the favorable outcome is staying with the service and the unfavorable outcome is churning. A persuadable stays when offered a promotion but churns without it, making the subscriber a candidate for targeted intervention. section 8.3.3

Figure 8.5 In attempts to influence behavior, we break down the target population into these four segments. Given limited resources, we want to target our influence efforts on the persuadables and avoid the others, especially the sleeping dogs.
figure

Use the population-segmentation figure to compare persuadables with sure things, lost causes, and sleeping dogs when allocating limited promotional resources. section 8.3.3

How Causal AI covers it

How deep it goes
Defines the segment through binary counterfactual outcomes and contrasts it with three response types, stopping at high-level segmentation.
Examples
Uses subscriber churn, retention promotions, and four population segments as concrete examples.
What you can do after
Apply via uplift modeling to prioritize people likely to benefit from a promotion.
How it connects
Connects counterfactuals, uplift modeling, promotions, churn, and treatment response.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Causal AI. The section links point to the parts of the book it draws on.