Analyze donor retention and find lapsed donors to win back
A retention analysis using LYBUNT and SYBUNT segments, upgrade and downgrade patterns, and a prioritized win-back plan.
The prompt
Help me analyze donor retention from our donor database export.
Data: [PASTE or describe columns: donor ID, gift date, amount, campaign or appeal, channel, donor type, first gift date]
Years covered: [e.g. 2021-2025]
Fiscal year: [e.g. July-June]
Questions I need answered: [e.g. why revenue is flat while donor count is falling]
Calculate and explain:
1. Overall donor retention rate year over year (donors who gave last year and again this year / donors last year), plus dollar retention.
2. First-year donor retention vs. repeat donor retention, reported separately.
3. LYBUNT (gave Last Year But Unfortunately Not This year) and SYBUNT (Some Year But Unfortunately Not This year) counts and dollars.
4. Gains and losses: new, recaptured, upgraded, same, downgraded, and lapsed donors, in donors and dollars.
5. Retention by acquisition channel, gift size band, and whether donors are monthly givers.
6. Data quality problems that distort the numbers (duplicates, soft credits, DAF or employer-match gifts credited to the wrong donor, missing dates).
Then give me:
- The 3 findings that matter most, in plain language for my board.
- A win-back plan for LYBUNT donors, prioritized by past giving, with a message angle for each segment.
- Changes to our first-year donor stewardship.
If you cannot run calculations directly, give me spreadsheet formulas or a pivot-table setup. Do not invent sector benchmarks; leave [ADD BENCHMARK] where a comparison would help.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. 2021-2025
- e.g. July-June
- e.g. why revenue is flat while donor count is falling
- ADD BENCHMARK
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Break down why a number changed between two periodsA driver breakdown and bridge that shows exactly which segments, volume, price, or mix effects caused a metric to move.
- Evaluate a statistical forecast's accuracy and explain the missesA backtest and error review of a demand or revenue forecast against simple benchmarks, showing where it misses and how to improve it.
- Find out why overtime is rising and how to cut itAn analysis of overtime data that separates demand, staffing, and process causes, with targeted actions to reduce it.
- Solve an Excel or Google Sheets problemGets you the right formula, pivot, or approach — with an explanation you can reuse.