> ## 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.

# What Allyy can predict

> The catalogue of models, grouped by the fundraising question they answer

Every Allyy model answers one question about a supporter. They split two ways:

* **By outcome** — a model either estimates a **probability** (classification, e.g. *will they respond?*) or an **amount** (regression, e.g. *how much will they give?*).
* **By scope** — a model is either about a **specific action** ("if we mail this person now, what happens?") or about a **supporter's trajectory** ("what will this person do over the coming year?").

<Note>
  The models are independent — use one on its own or combine several. Which ones fit your programme is something we'll scope with you.
</Note>

## Two ways to slice the catalogue

Every model sits in one cell of this grid — outcome down the side, scope across the top. That's usually enough to find the one you need.

|                                 | **Specific action** — a mailing or call         | **Supporter trajectory** — over time                                                             |
| ------------------------------- | ----------------------------------------------- | ------------------------------------------------------------------------------------------------ |
| **Probability** — *how likely?* | DM propensity · TM reachability · TM conversion | Active donor · Middle donor · Reactivating donor · Subscription acquisition · Subscription churn |
| **Amount** — *how much?*        | DM expected amount                              | Lifetime value *(roadmap)*                                                                       |

## Where each model fits the supporter journey

As a supporter moves through their relationship with you, a different model supports the next decision.

| Stage                    | What's happening               | Model that helps                                               |
| ------------------------ | ------------------------------ | -------------------------------------------------------------- |
| Prospect / one-off donor | first or occasional gifts      | DM propensity, TM reachability, TM conversion — target the ask |
| One-off → regular giver  | converting to a recurring gift | Subscription acquisition                                       |
| Growing supporter        | value rising                   | Middle donor                                                   |
| Active supporter         | giving steadily                | Active donor — will they give again?                           |
| Regular giver at risk    | may cancel their mandate       | Subscription churn                                             |
| Lapsed                   | stopped giving                 | Reactivating donor — win them back                             |

## Targeting a campaign — who to contact

<CardGroup cols={2}>
  <Card title="DM propensity" icon="envelope" href="/models/dm-propensity">
    Will this supporter respond to a mailing? Use it to rank a mailing list and cut volume without losing income.
  </Card>

  <Card title="TM reachability" icon="phone" href="/models/tm-reachability">
    Will we actually reach this person by phone? Prioritise dialling lists.
  </Card>

  <Card title="TM conversion" icon="phone-volume" href="/models/tm-conversion">
    Given we reach them, will they accept the offer? Focus calls on likely converters.
  </Card>

  <Card title="Email engagement" icon="at">
    Will this supporter open or click? Prioritise digital sends.
  </Card>
</CardGroup>

## How much to ask — the value of an action

<CardGroup cols={2}>
  <Card title="Expected amount" icon="coins" href="/models/dm-expected-amount">
    How much is this supporter likely to give in response to this action? Combine with propensity to target on **expected revenue**, not just likelihood.
  </Card>

  <Card title="Ask amount" icon="sliders">
    What set of suggested amounts (the "ask string", e.g. €20 / €50 / €100) maximises yield for this supporter?
  </Card>
</CardGroup>

## Keeping supporters — retention & risk

<CardGroup cols={2}>
  <Card title="Subscription churn" icon="user-xmark" href="/models/subscription-churn">
    Will a regular giver cancel their direct debit in the coming months? Drives save / win-back programmes.
  </Card>

  <Card title="Active donor" icon="heart" href="/models/active-donor">
    Will a currently active supporter give again in the next 12 months?
  </Card>

  <Card title="Middle donor" icon="arrow-trend-up" href="/models/middle-donor">
    Retention focused on the valuable "middle" segment — where small movements move a lot of income.
  </Card>

  <Card title="Reactivating donor" icon="rotate-left" href="/models/reactivating-donor">
    Will a lapsed donor come back if we ask? Prioritise win-back appeals by likelihood to respond.
  </Card>

  <Card title="Subscription acquisition" icon="user-plus" href="/models/subscription-acquisition">
    Will a one-off donor convert to a recurring gift? Find your best regular-giving prospects.
  </Card>
</CardGroup>

## Long-term value

<CardGroup cols={2}>
  <Card title="Lifetime value (LTV)" icon="gem">
    What is this supporter worth over a multi-year horizon? Drives stewardship investment.
  </Card>

  <Card title="Donation frequency" icon="repeat">
    How many gifts will this supporter make in the next year?
  </Card>
</CardGroup>

## Timing — when something will happen

<CardGroup cols={2}>
  <Card title="Time to next gift" icon="clock">
    How long until this supporter is likely to give again?
  </Card>

  <Card title="Time to churn" icon="hourglass-half">
    When is a supporter likely to stop giving?
  </Card>
</CardGroup>

## How models combine

The models are designed to work together — combined, they describe a supporter more completely than any one alone:

* **Propensity × expected amount** — rank a mailing or call list on expected revenue (likelihood × value), not likelihood alone.
* **Subscription churn × lifetime value** — retention effort weighed against the recurring income at stake.
* **Active donor and reactivating donor** — the same supporter, before and after they lapse.

See [Create & train a model](/processes/model) to set one up.