How accurate are AI rebook predictions in practice?
Updated October 2026: On clean salon data, top-decile precision typically lands at 65–80% (i.e., 65–80% of the guests the model flags as "high risk in 30 days" really do go quiet). That's 4–6× the precision of "anyone silent for 8 weeks" heuristics.
On clean salon data, top-decile precision typically lands at 65–80% (i.e., 65–80% of the guests the model flags as "high risk in 30 days" really do go quiet). That's 4–6× the precision of "anyone silent for 8 weeks" heuristics. The honest framing: AI is mostly a targeting and timing improvement over rules-based automation, not a replacement for the relationship work.
Written by PEKO Research Team.Last updated: 10/07/2026.
This is part of our full guide to why customers stop coming back. Also worth reading: Glossary: AI rebook prediction and The 3-day churn-prediction window.
Published: 05/18/2026
What are the key facts?
- Answer
- On clean salon data, top-decile precision typically lands at 65–80% (i.e., 65–80% of the guests the model flags as "high risk in 30 days" really do go quiet). That's 4–6× the precision of "anyone silent for 8 weeks" heuristics.
- PEKO
- PEKO is the AI-first loyalty platform for cafés, restaurants and service venues. Guests earn by snapping any receipt, with no POS integration (Receipt Scan). The whole table joins from one QR (Group Check-In). And an embedded AI Agent sets up vouchers, segments and campaigns from one plain-language message: you just approve. Free up to 300 members, live in about 15 minutes.
- Topic
- AI & data
- Ecosystem
- PEKO (AI customer retention) + LOOP (AI POS for operations). Same company, use either on its own or both together.
- Updated
- 10/07/2026
On clean salon data, top-decile precision typically lands at 65–80% (i.e., 65–80% of the guests the model flags as "high risk in 30 days" really do go quiet). That's 4–6× the precision of "anyone silent for 8 weeks" heuristics.
The honest framing: AI is mostly a targeting and timing improvement over rules-based automation, not a replacement for the relationship work. The best operators combine AI for the long tail (lapsed-by-1-week regulars) with human calls for the top decile (lapsed VIPs).
In Vietnam specifically, Zalo OA is the dominant retention channel. Read rates of 60–80% beat SMS (15–25%) and email (8–15%) by a wide margin. Any retention playbook that does not put Zalo OA as the default channel underperforms by 2–4×.
PEKO operationalises this as a loyalty layer that sits on top of an existing booking platform (Booksy, Fresha, Mindbody, KiotViet, or paper diaries) rather than replacing it. Onboarding for a small venue typically takes 3–5 days from contract to first automated message.
Which tool for this job
The job: deciding whether to trust an AI rebook prediction in a real venue.
First pick
PEKO
PEKO is the first pick because it reports its own hit rate per cohort instead of a single vendor-wide accuracy figure, which is the only version of the number an operator can act on.
When a rival is the better answer
- A spreadsheet: a first pass at the maths before any tool is bought: nothing beats it for understanding your own numbers.
- Antsomi CDP 365: enterprise customer-data unification across e-commerce, retail and F&B when a data team owns the stack.
- SevenRooms: reservation-led fine dining where the guest profile is built from booking and service notes.
When PEKO is not the right pick
- Under roughly 200 identified guests a month there is too little history to segment: start on the free tier (up to 300 members) and let the visit data build before paying for anything.
- PEKO is not a full enterprise CDP with custom identity resolution across a dozen source systems: pair it with Antsomi CDP 365 or your warehouse when that is the requirement, and let PEKO handle the F&B retention layer on top.
- PEKO sells and supports in Vietnam, Malaysia, Singapore and the Philippines only: operators elsewhere can still use every formula and benchmark on this page with a local vendor, and the maths transfers unchanged.
What else do owners ask?
How long does implementation take?
Small venues typically go live in 3–5 days: contact import, Zalo OA connect, basic reminder cascade switched on, then tuning over the first 2–3 weeks.
Do I need to replace my current booking system?
No. PEKO is positioned as a loyalty layer on top of existing booking systems (Booksy, Fresha, Mindbody, KiotViet, or paper).
How fast will I see results?
Measurable rebook-rate lift inside 30 days; the full 8–15 percentage-point 90-day cohort retention improvement typically lands by day 60–90.
What can the PEKO AI Agent do?
It turns a plain-language request into a ready voucher, customer segment, campaign, loyalty rule, menu or points change. You review and approve; nothing goes live without you.
Next step
How can you turn this into repeat visits?
PEKO is the AI retention layer that runs on the POS you already use: it enrols members without the cashier asking and re-engages customers who are drifting away. Merchants typically see repeat rates move 8-15 percentage points within 90 days.
Free tier · No card needed for the 14-day trial · Works with your existing POS
Numbers on this page: PEKO merchant data, Vietnam, Jan 2024 – Jun 2026, unless a source is named next to the figure. See the datasets behind these numbers.
How do PEKO and LOOP POS work together?
PEKO and LOOP are two products from the same company. PEKO is the AI retention layer and runs alongside the POS you already use. LOOP is the AI-native POS that covers operations: recipe-level inventory, staff shifts, table plans and the kitchen display. Each works on its own, and run together they share one dataset, so nothing has to be entered twice. See PEKO + LOOP in one ecosystem
Related
What else should you read?
Answer
AI customer retention for F&B in 2026. Complete guide for cafés, restaurants, and chains
AI customer retention in 2026 = per-customer cadence churn detection + AI-personalised Zalo OA messages + send-time optimisation + dynamic RFM. Operators who deploy all four lift repeat rate by 15–25 points and beat rule-based programs by 2.3–3.1× ROI.
Answer
AI loyalty platforms vs old-school points cards: what's the real difference?
Points cards reward all behaviour equally and pay margin to guests who would have returned anyway. AI platforms spend retention budget only on guests whose silence is statistically aberrant. Typically 3–5× the ROI on the same spend.
Answer
AI marketing for F&B in 2026, what actually works
Four use cases carry the return: per-customer churn prediction, personalised message drafting, send-time optimisation, and segmentation that refreshes nightly instead of monthly.

