Lost cause

As explained in Causal AI

A lost cause is a person who would experience the undesirable outcome regardless of whether the promotion or treatment is applied.

A lost cause is a person who will experience the undesirable outcome regardless of whether a promotion or other treatment is applied. In churn analysis, the subscriber leaves with or without the promotion. section 8.3.3

Lost causes are non-responders: treatment does not change their outcome. They differ from sure things, who remain regardless; persuadables, who benefit from treatment; and sleeping dogs, who are harmed by it. section 8.3.3

Promotion and churn

A retention promotion sent to a lost cause spends incentive value without preventing churn. Uplift targeting therefore seeks persuadables and avoids lost causes, sure things, and especially sleeping dogs. 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.

Use the four-segment diagram to compare lost causes with the other counterfactual response groups and identify why targeting matters. section 8.3.3

How Causal AI covers it

How deep it goes

Defines lost causes through binary counterfactual outcomes and contrasts them with three response segments, stopping short of an identification procedure.

Examples

Uses subscribers receiving retention promotions and classifies their possible churn responses into four counterfactual segments.

What it assumes

Assumes a binary promotion and outcome while introducing counterfactual reasoning through subscriber churn.

What you can do after

Apply uplift modeling to prioritize persuadables and avoid targeting lost causes.

How it connects

Connects lost causes to uplift modeling, binary counterfactuals, churn, treatment targeting, and sleeping dogs.

liveBookmanning.com

Read Causal AI on liveBook Get the book at manning.com

Related concepts

• clusteringproduced by · Clustering is the technique of grouping data items according to similarity or shared characteristics.

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.