Glossary /

    RFM analysis

    Written by PEKO Team.Last updated: 21/05/2026.

    RFM analysis is a customer segmentation method that scores each customer on Recency (how recently they visited), Frequency (how often), and Monetary value (how much they spend).

    Published: 01/05/2026

    RFM gives every customer three scores, usually 1–5, then combines them into a segment label like 'Champions' (high R, F, M), 'At Risk' (low R, high F, high M), or 'Hibernating' (low across the board).

    For restaurants, RFM is a much sharper tool than blanket promotions. Sending a 20% discount to a Champion is wasted margin — they'd come back anyway. Sending the same discount to an At Risk regular might be the only thing that pulls them back from churn.

    Modern AI tools like PEKO automate RFM scoring daily and trigger different campaigns per segment, so your win-back budget goes only where it actually moves the needle.

    Worked example

    A guest who visited yesterday (R=5), comes 8× per month (F=5), and spends $45 per visit (M=5) is a 555 'Champion'. A guest who hasn't been in for 60 days (R=2) but used to come weekly with high tickets (F=5, M=5) is a 255 'At Risk' — your highest-priority win-back target.

    FAQ

    How is RFM analysis different from customer segmentation?

    RFM is one specific type of segmentation. General segmentation can use anything (demographics, dish preference, channel). RFM is purely behavioural and works without any personal data — making it both privacy-friendly and reliably predictive.

    Do I need a data scientist to run RFM analysis?

    No. Modern loyalty platforms run RFM scoring automatically on your POS data and update segments daily. PEKO does this out of the box.

    Sources

    The definitions and figures on this page reference the sources below:

    Related terms

    People also read