AI forecasting for Tet peak demand: the 6-week playbook for Vietnamese F&B

AI forecasting for Tet peak demand: the 6-week playbook for Vietnamese F&B

2026 benchmark: Median food cost across SEA QSR chains: 30–34% in 2026.

Why Tet breaks normal forecasting

Most F&B forecasting models (and most Excel rules-of-thumb) assume:

• Demand has weekly seasonality
• Last year's same week is the best baseline
• Staffing scales linearly with covers
• Suppliers deliver on a normal cadence

Tet violates all four:

1. Demand swings ±60% across 14 days, dine-in collapses Day -3 to Day +3, takeaway/delivery spikes Day -7 to Day -1, family hotpot/buffet venues spike Day +4 to +10
2. Lunar calendar shifts mean "same week last year" can be 10–14 days off the real comparable
3. Staff availability collapses, many staff return to hometown; the ones who stay command 1.5–2x premium pay
4. Suppliers shut for 5–9 days; cold-chain proteins and fresh produce need to be pre-positioned

A chain that misses by ±35% (typical for Excel-based planning) faces either ₫200–500M of dead stock locked up until Q2, or angry customers and empty shelves during the highest-margin week of the year.

What an AI Tet forecast actually does differently

1. Lunar-aligned baseline, compares Day -7 to Day +14 across the last 3 Tet windows, not calendar weeks
2. Decomposition by occasion (separates dine-in, takeaway, delivery, gift sets, catering) each behaves differently
3. Local event overlay (flowers market dates, fireworks locations, temple foot-traffic) pulled from regional calendars
4. Weather adjustment, North vs South Vietnam Tet weather diverges and shifts demand mix (hotpot vs cold dessert)
5. Supplier-shutdown buffer, computes pre-Tet pull-forward and post-Tet ramp separately

Output: a daily forecast for the 21-day Tet window, by category, by outlet, with confidence intervals.

The 6-week playbook (T-6 to T+2)

Week T-6 to T-5: Data prep

• Pull last 3 Tet windows of POS data (daily, by category, by channel, by outlet)
• Tag each historical day with lunar date offset
• Identify outliers (Covid 2020/21, supplier outages) and decide whether to include or down-weight

Week T-4: Demand forecast

• Run model → daily forecast by SKU category and channel for Day -7 to Day +14
• Owner reviews; manual overrides for known events (new outlet, menu change vs last Tet)
• Lock the demand forecast, this is now the source of truth for all downstream decisions

Week T-3: Procurement plan

• Translate demand into ingredient quantities using current recipes
• For each SKU: split into "pre-Tet stockpile" (shelf-stable + frozen) and "during-Tet just-in-time" (fresh)
• Issue PO calendar to suppliers; lock prices; secure cold storage capacity
• Build a 3-day buffer for proteins (the supplier-shutdown risk hedge)

Week T-2: Staffing plan

• Forecast labor hours by day and by station
• Identify staffing gaps; offer Tet premiums to retain (cheaper than agency replacements)
• Pre-book agency backup for Day 0 to Day +3 (the hardest days)

Week T-1: Communication + final tune

• Push Tet hours, special menus, gift sets to Zalo OA, GrabFood, Shopee Food
• Re-run forecast with last week's actuals, small adjustments only, no major redos
• Brief each outlet manager on their daily target and staffing

T+1 to T+2 (post-Tet)

• Daily reconciliation: actual vs forecast by outlet
• Capture every variance >15% with a written reason, this is the gold for next year's model
• Liquidate any pre-Tet surplus within 10 days (deep discount > dead stock)

Real case: 11-outlet Vietnamese restaurant group

An 11-outlet group (mixed pho + rice + buffet formats, ₫9.4B/month) historically planned Tet on Excel + senior-manager intuition. Last 3 years:

• Tet 2023: forecast error ±32%, dead stock ₫340M
• Tet 2024: ±28%, dead stock ₫280M, also a stockout on premium beef Day -2
• Tet 2025: ±34% (new outlet threw the model off)

For Tet 2026 they used their POS's built-in AI forecaster + the 6-week playbook above.

Result

• Forecast error: ±8.4% chain-wide (range across outlets: 4–14%)
• Dead stock post-Tet: ₫46M (vs ~₫300M historical average)
• Stockouts: 0 major incidents
• Tet-window revenue: ₫2.1B (+11% YoY)
• Tet-window margin: +3.2 pts vs Tet 2025 (lower waste + better mix)

The single biggest contributor to the improvement wasn't the model, it was the lunar-aligned baseline. Comparing Day -3 Tet 2026 to Day -3 Tet 2025 instead of "the Friday before Tet" eliminated most of the historical noise.

What you can do this week, even without AI

1. Re-baseline last 3 Tets in a spreadsheet using lunar day offsets, not calendar dates
2. Decompose by channel (dine-in vs takeaway vs delivery vs gift sets) and forecast each separately
3. Build a supplier-shutdown calendar with each supplier's exact close/reopen dates
4. Pre-commit 60% of perishable orders by T-2 weeks; hold 40% as adjustable
5. Set a hard rule: no SKU stockpiled beyond 12 days of expected sales

Tet doesn't reward optimism. It rewards the chain that did the math 6 weeks earlier than everyone else.

Related reading

• AI demand forecasting for Tet and peak season in F&B
• AI fair shift scheduling when your margin is paper-thin
• AI A/B Menu Pricing: Test Prices Per Outlet Without Spreadsheets

---

Why this matters in 2026

Multi-outlet F&B operators across Vietnam and Southeast Asia are running into the same wall in 2026: aggregator commissions compress margins, food-cost drift compounds across outlets, labour cost climbs faster than ticket size, and a traditional POS only surfaces the damage at month-end when the only response left is firefighting. Operators who win in 2026 close the loop in hours, not weeks, variance flags before the next shift, demand forecasts before purchasing, daypart promos drafted automatically for slow slots, and a single morning brief instead of five dashboards. That is the bar this guide is written against, and the reason LOOP exists. The cost of a missed signal is no longer a single bad week, it is the difference between a chain that compounds outlet-level profitability and a chain that opens new outlets to mask the leaks at the old ones.

Operator playbook, first 30 days on LOOP

Week 1: Foundations. Import menu, recipes, modifiers, customers, loyalty balances and 24 months of sales via CSV. Connect aggregators (GrabFood, ShopeeFood, Be). Configure e-invoice provider (MISA / Viettel / VNPT). Confirm payment rails (VietQR for VN; DuitNow, PayNow and QR Ph are on roadmap). Train two staff per outlet on voice and text commands; the rest pick it up by observation in days 4–7.

Week 2: Variance and forecast online. Switch demand forecasting on at daypart level. Set variance alert thresholds (default: food-cost ±3pp, labour ±2pp, void rate ±0.5pp). Let the system run a full week without intervention so the baseline calibrates. Review the morning brief each day; ignore the urge to override, by day 10 the forecast typically holds steady.

Week 3: Promo and loyalty loop. Turn on daypart promo drafting for the two slowest hours per outlet. Connect Zalo OA / LINE / WhatsApp for delivery; start with a single segment (e.g. lapsed-30-day) and a single offer. Measure incremental visits, not coupon redemptions.

Week 4: Compound. Roll the same flow to a second outlet, then a third. The operating model is the same at outlet 2 as outlet 20, that is the point of LOOP.

KPI table, what to watch

Common pitfalls SEA operators hit in 2026

Treating aggregator orders as a separate business. Operators who keep five aggregator tablets running in parallel lose roughly 4–7 minutes per peak hour to context-switching alone, and miss the per-aggregator margin picture entirely. Unifying the queue (one tablet, one KDS, one accounting line per aggregator) is usually the single highest-leverage move in the first 60 days.

Letting variance live in spreadsheets. A weekly food-cost review is a 7-day reaction time on a 24-hour problem. Variance has to live in the operating layer, flagged, attributed and routed to the responsible manager within hours, not aggregated to a Friday email.

Loyalty as a punch card. A 2026 loyalty programme is a messaging channel with attribution. If the only metric is "points issued", the programme is a cost centre. If the metric is "incremental repeat visits per segment per month", it compounds.

Forecasting at the wrong resolution. Chain-level forecasts are wallpaper. Daypart-and-outlet is the smallest unit that pays back, coarser is too vague to act on, finer is noise.

How LOOP solves this

LOOP is an AI-native restaurant operating system built for SEA F&B chains. Operators run their venues by voice or text command instead of clicking through dashboards. AI forecasts demand per outlet at daypart resolution (modelled accuracy published in our methodology), flags food-cost and labour variance within hours of the shift closing, drafts promos for slow daypart slots and pushes them to Zalo OA / LINE / WhatsApp, and delivers a three-item morning brief at 06:30 local time so the operator's first action of the day is informed. LOOP unifies GrabFood, ShopeeFood, Be into one queue, supports VietQR in Vietnam; DuitNow, PayNow and QR Ph are on roadmap, and ships VAT e-invoice (TT78) via MISA, Viettel and VNPT. Pairs with PEKO loyalty. PEKO customers get 50% off LOOP POS paid plans.

Under the hood, LOOP is offline-first with a 90-second resync window so orders, payments and KDS keep firing through ISP drops; recipe-level COGS is computed at order time so every plate's contribution margin is visible before the shift ends; and the morning brief is generated from the previous day's variance, the current day's forecast and the next 14 days of bookings, weather and local events, not a static template. The result is fewer dashboards, faster decisions, and a noticeably calmer week for the operator.

Related guides

• LOOP blog: AI POS guides for SEA
• LOOP POS
• PEKO loyalty
• VeLoop delivery aggregator unification
• LOOP pricing
• Compare LOOP vs other POS

FAQ

How fast can a SEA F&B chain switch to LOOP?

Typical cutover for 2–10 outlets is 5–10 business days: CSV import of menu, recipes, customers, loyalty and 24 months of sales, parallel run over a weekend, then cut over Monday open. Larger chains (20+ outlets) usually phase by region over 4–6 weeks.

Does LOOP work without stable internet?

Yes. LOOP runs offline-first with a 90-second resync window. Orders, payments and KDS keep firing during ISP drops; the cloud reconciles automatically on reconnect. Aggregator orders queue locally and dispatch when the link returns.

What does LOOP cost?

Per-outlet monthly pricing with no per-device upcharge. PEKO customers get 50% off LOOP POS paid plans. See pricing for current plans.

Does LOOP support VAT e-invoice (TT78)?

Yes. LOOP integrates with MISA, Viettel and VNPT as e-invoice providers. Issuance is automatic at order close and reconciles end-of-day.

Which payment rails does LOOP support?

LOOP POS supports VietQR, MoMo and ZaloPay in Vietnam. PayNow, NETS QR, SGQR, DuitNow QR, Touch 'n Go, QR Ph, GCash and Maya integrations are on roadmap; outlets can record payments from their existing terminals.

<!-- enriched:v1 -->