> ## Documentation Index
> Fetch the complete documentation index at: https://docs.allyy.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Reactivating donor

> Will a lapsed donor come back if we ask?

Predicts which lapsed donors are most likely to give again — so win-back budget goes where it can actually recover income.

**What it predicts** — For lapsed supporters, the probability they give again in the next window.

**Who it scores** — Genuinely lapsed donors: people who gave at some point in the longer history (e.g. within five years) but *not* in the recent period (e.g. the last year). Currently-active donors are excluded.

**The decision it drives** — Prioritise win-back appeals: spend reactivation budget on the lapsed supporters most likely to respond, and leave the truly gone alone.

**Worked example** — A reactivation mailing to the whole lapsed file is expensive. Scoring it first, the team mails the top-ranked half and recovers most of the win-backs at far lower cost.

**What good looks like** — More reactivations per euro of win-back spend.

<Tip>
  **Pairs well with [Active donor](/models/active-donor)** — which catches supporters *before* they reach the lapsed stage.
</Tip>

<CardGroup cols={2}>
  <Card title="All models" icon="table-cells" href="/models/what-allyy-can-predict">
    Back to the full catalogue.
  </Card>

  <Card title="Create & train a model" icon="wrench" href="/processes/model">
    Set one up on your own data.
  </Card>
</CardGroup>