Machine Learning for Selecting Letter Recipients
Why Is It Worthwhile?
Fundraising letters remain one of the most effective channels in the non‑profit sector, yet they generate significant postage and printing costs—as well as CO₂ emissions. Our solution: write only to people with a high probability of donating. Many organisations still rely on simple heuristics such as “Anyone who ignored five mailings …”. Such rules are too coarse and often poorly substantiated; they waste potential and drive costs up. At the same time, they lack the flexibility an organisation needs if, for example, it wants to strategically improve the ROI of its fundraising letters.
Our Approach
We design and train an organisation‑specific machine‑learning model that predicts the expected donation revenue for every person in your database. The model is using your historical fundraising data. You then define a threshold (e.g. twice the printing and postage costs) and send letters only to recipients predicted to exceed that value. After each mailing, the model updated the new data and thereby continues to learn.
How It Works – Three Steps
- Feed the data – donation history, postcode, membership status, payment methods …
- Train the model – We work with you to decide which model type is the best fit and then train the model on your data.
- Select recipients – set the threshold, export the list, send the mailing.
Real‑World Results: 6.3% more surplus
In collaboration with one of our clients, we developed a machine‑learning model for selecting letter recipients. By now, the organisation has used this model, retraining it continuously with fresh data. Evaluations show that the model accurately predicts who will donate—and how much—enabling the organisation to mail more precisely and profitably.
The example also demonstrates that with just a few tens of thousands of letters sent and several thousand individual donations, a model can already predict the expected donation per person.
Your Benefits at a Glance
- Save postage or increase revenue – you define the minimum value; each letter must pay off.
- Automatic learning – the model refines itself after every mailing.
- Transparency instead of a black box – models like decision trees or EBMs deliver comprehensible rules and visualisations.
- Privacy first – we use only open‑source tools and custom software on encrypted servers in our office; your data never enters the cloud.
- Climate benefit – less printing means less paper and less CO₂.
Possible Objections
Privacy? – We do not use large language models (LLMs) on corporate platforms such as ChatGPT; we rely on open‑source tools that run locally on fully encrypted machines in our office.
Black box? – Transparency is crucial for our client. That’s why we rely on an explainable model (decision tree) that makes recipient selection understandable for everyone. More‑complex methods such as random forests or Explainable Boosting Machines also be explained, but they are less intuitive to grasp.
Our Clients
We work with different clients on this, among them Wikimedia Deutschland and Digitalcourage.
Background: What Is Machine Learning?
Machine learning (ML) builds statistical models that learn from historical data in order to make predictions or decisions for new, unseen data. Unlike large language models (LLMs), which aim to generate plausible text and operate as black boxes, classic machine‑learning methods focus on structured features (e.g. age, donation history, postcode) and are therefore much leaner, more resource‑efficient and easier to control. A key advantage is the explainable nature of many techniques:
- Intrinsic explainability – models that are transparent by design, such as decision trees; every branch represents a concrete if‑then rule users can directly follow.
- Post‑hoc explainability – more‑complex methods such as random forests or boosting algorithms can also be interpreted with techniques like SHAP values or LIME, but they are less intuitive.
For our client we deliberately chose a decision tree: its clear branches reveal which features (e.g. recent donation frequency, total past contributions, payment method) lead to which selection, thereby increasing transparency for all involved.
How does ML‑based selection work? Unlike simple heuristics, the resulting models can identify complex relationships between variables, improving predictive accuracy. Even data‑sparing organisations usually have enough basic information to train a model: postcode, past mailings, date and amount of previous donations (by payment method), membership status, etc.
Fictional Example – Trees4Teuto
The fictional forest‑conservation NGO Trees4Teuto wants to maximise the total donations from its next letter campaign and opts for an easy‑to‑understand decision tree.
We would build an interface to Trees4Teuto’s database to import past mailing data and potential recipient data into our software package. We do not extract names, addresses, bank details, etc. (Interfaces currently exist for OpenMove and CiviCRM).
From these data we create a decision tree that might include the following leaves:
| Leaf | Criterion | Expected value per letter |
|---|---|---|
| 1 | Total donations > €200 & mailings since last donation > 5 & last payment via PayPal | €1.34 |
| 2 | Total donations ≤ €200 & mailings since last donation > 5 & last payment via PayPal | €0.60 |
| 3 | Total donations > €200 & mailings since last donation ≤ 5 & last payment via bank transfer | €5.67 |
(This is a simplified example; in reality there are more like two dozen rules.)
Trees4Teuto sets a minimum return of €1.20 per letter and therefore selects everyone from leaves 1 and 3 for the mailing. This cuts postage costs, saves paper and significantly increases the net benefit of the campaign.
German article
In September 2025 the German Fundraising-Magazin published our approach. (Sorry, German only)
Curious?
Let’s talk:
Phone Signal (and other messengers): +49 177 3068911