How do you read a visit heatmap to find an F&B venue's true peak hours?
Updated October 2026: Plot transactions on a 7-day × 24-hour grid, then normalise by staffing cost. A 'peak' is only profitable if revenue per staff-hour exceeds 2.4× the hourly wage. Most cafés have one fake peak (Saturday 14:00) that loses money.
Plot transactions on a 7-day × 24-hour grid, then normalise by staffing cost. A 'peak' is only profitable if revenue per staff-hour exceeds 2.4× the hourly wage. Most cafés have one fake peak (Saturday 14:00) that loses money. A visit heatmap is a 7-row by 24-column grid where each cell is the count or revenue of transactions in that hour-of-week.
Written by PEKO Research Team.Last updated: 10/07/2026.
Published: 05/24/2026
What are the key facts?
- Answer
- Plot transactions on a 7-day × 24-hour grid, then normalise by staffing cost. A 'peak' is only profitable if revenue per staff-hour exceeds 2.4× the hourly wage. Most cafés have one fake peak (Saturday 14:00) that loses money.
- 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
A visit heatmap is a 7-row by 24-column grid where each cell is the count or revenue of transactions in that hour-of-week. Raw transaction heatmaps are misleading: a busy Saturday 14:00 lunch tail looks like a peak but usually loses money because staffing is still at peak level while throughput has dropped.
The fix is to normalise each cell by labour cost and overhead, producing a profit-per-hour heatmap. Cells that exceed 2.4× the hourly wage in gross contribution are real peaks worth promoting. Cells under 1.0× are candidates for promo-led traffic shifting or staff trimming.
Use a 168-cell grid
Hour-of-week, not day-of-week. The 'Tuesday 19:00' pattern is invisible if you aggregate by day.
Overlay loyalty visits
Members typically over-index on weeknight 18:00–20:00 windows. Promo those windows with tier-bonus multipliers to deepen the relationship.
Flag fake peaks
If revenue is high but profit-per-staff-hour is below 1.5×, you're paying for the peak. Shift promo demand into the adjacent valley instead of stacking more on the peak.
What else do owners ask?
How many weeks of data do I need?
Six weeks minimum to smooth out weather, holidays, and stock-outs. Twelve weeks is the cleanest signal for an independent café.
Does PEKO generate this heatmap?
Yes. The Visit Heatmap dashboard renders the 168-cell grid by branch, supports the labour-normalised view, and lets you draw a window to push a flash promo through ZNS to members likely to come in that slot.
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
Which related topics should you explore?
What else should you read?
Answer
CLV formula for restaurants and cafés (with calculator)
CLV = contribution margin per visit × visits per year × years retained. A café regular spending $6 at 55% margin, 18 visits a year for 1.6 years is worth about $95 in gross profit.
Answer
How do you measure average order value uplift from a loyalty program?
AOV uplift = (member AOV − matched non-member AOV) ÷ non-member AOV. A well-tiered F&B program delivers 11–22% AOV uplift; tier-only programs without targeted offers usually plateau at 4–7%.
Answer
What is a realistic referral k-factor for an F&B loyalty program?
K-factor for an F&B loyalty program rarely exceeds 0.35. A healthy independent café or restaurant lands at k = 0.18–0.28, meaning every 100 active members bring in 18–28 new enrolments per cycle. Above 0.5 typically indicates incentive abuse.

