Group customers by buying behaviour (RFM)

Prompt that splits customers into a few groups by last purchase, purchase frequency and revenue, with a fitting action for each. Paste it into an AI tool of your choice, which then groups the customers.

Topic: Spreadsheets & data
Type: Prompt
Level: Intermediate
Time: about 10 min

Results depend on the tool, the model and what you enter.

Result preview

Example: written by our editors, not real AI output.

Cut-offs (12 months): last purchase up to 60 / 61 to 180 / over 180 days; purchases 1 / 2 to 4 / 5 or more; revenue up to €50 / €51 to €200 / over €200 1. Loyal regulars: 140 customer numbers, 46% of revenue → early access to new products 2. New customers: 310, 12% → second purchase with care tips for the product 3. Formerly active: 220, 18% → ask what was missing 4. One-time buyers: 900, 9% → no special campaign, only the regular newsletter with consent Check: 12 customer numbers with over 40 purchases are probably business customers.

Fill in

What you type stays in this browser window. We store and send nothing.

BusinessWhat do you sell?

PeriodWhich period?

DataPaste orders with customer number, date and amount, without names or addresses

Your prompt

Group our customers by buying behaviour using the RFM method.
Business: [Business]
Period of the data: [Period]
Data:
<data>
[Data]
</data>
Approach: 1. For each customer number, calculate three values: days since the last purchase (R), number of purchases (F) and revenue (M) in the period. 2. Split each value into three levels and explain the cut-off points instead of setting them without checking. 3. From this, form no more than six groups with clear names, such as loyal regulars, new customers, one-time buyers, formerly active. 4. For each group, give the count, share of revenue and one action that suits the group. 5. Show the formulas or steps so that I can rebuild the analysis in the spreadsheet. Work only with customer numbers, not names or contact details, and mark anomalies such as returns or business purchases with "Check:".

Take particular care to disclose the group cut-offs and work only with customer numbers instead of personal data.

Before you answer, check: Are all instructions met? If key information is missing or a placeholder in square brackets is still in the text, ask instead of guessing. Mark assumptions as assumptions.

Group our customers by buying behaviour using the RFM method.
Business: [Business]
Period of the data: [Period]
Data:
<data>
[Data]
</data>
Approach: 1. For each customer number, calculate three values: days since the last purchase (R), number of purchases (F) and revenue (M) in the period. 2. Split each value into three levels and explain the cut-off points instead of setting them without checking. 3. From this, form no more than six groups with clear names, such as loyal regulars, new customers, one-time buyers, formerly active. 4. For each group, give the count, share of revenue and one action that suits the group. 5. Show the formulas or steps so that I can rebuild the analysis in the spreadsheet. Work only with customer numbers, not names or contact details, and mark anomalies such as returns or business purchases with "Check:".

Take particular care to disclose the group cut-offs and work only with customer numbers instead of personal data.

Before you answer, check: Are all instructions met? If key information is missing or a placeholder in square brackets is still in the text, ask instead of guessing. Mark assumptions as assumptions.

This is an instruction for an AI, not the result itself.

Where this prompt works

These AI tools are a good fit for this prompt:

How to use it

Fill in the fields or tap a suggestion. Leave out names, addresses and other personal data.
Copy the finished prompt into an AI tool of your choice.
Before any campaign, check that you may contact the group in this way, for example whether there is consent for email marketing.

Why does this work?

Three simple values are enough to tell loyal, new and lapsing customers apart. Explained cut-off points make the groups understandable and comparable later.

Tips

Seasonal products distort the "last purchase" value. In that case, choose a period that covers at least one full season.

You may use our prompts freely, including at work. Please do not republish them as your own collection. We give no warranty for AI results; check them yourself. Terms of use

Group customers by buying behaviour (RFM)

Result preview

Fill in

Your prompt

Where this prompt works

How to use it

Why does this work?

Tips

Part of these agents

Also a good fit

Check the unit of analysis in tests New

Find cardinality explosions in metrics New

Estimate customer lifetime value simply New