Platform/Forecasting
Forecasting

Turn your forecast into
a decision you can defend.

Build, update and measure one shared hotel forecast — without giving up the revenue manager's judgment.

Manual workflow, statistical baseline and monthly accuracy tracking are included in BI Core. Smart Forecast Enhanced adds a daily 60-day AI correction through Pulse AI.

app.peaqplus.com/forecast/2026-03
SIMULATED HOTEL · FORECAST · MARCH 2026
v3 · DRAFT
v1v2v3
DayOTBLY · SPBudgetSmart F.Final
Mar 05142 / €18.4k128 / €16.2k140 / €18k146146
Mar 06156 / €21.1k149 / €19.8k155 / €21k162160
Mar 07168 / €24.5k158 / €23.1k170 / €23.5k171171
Mar 08124 / €19.2k142 / €22.4k155 / €22k138138
Mar 09118 / €17.8k138 / €21.2k150 / €21.5k132132
Change reason required: Weekend pickup underperformance, lowering Mar 8–9.
One forecast, three decisions

Useful to the person building it — and the people relying on it.

The revenue manager needs control. The GM needs the variance. The owner needs to know whether the forecast deserves confidence.

RM
Update without rebuilding

Work by segment, day or both. Start from the statistical baseline, adjust what you know, and preserve every committed version with its reason.

Control + audit trail
GM
See where the plan is drifting

Read OTB, pace, last-year same point and forecast-versus-budget together, then focus the team on the dates that need a decision.

Exception before detail
OWN
Ask how accurate it was

Review monthly error metrics on the hotel's own actuals instead of accepting a model claim or a single unexplained percentage.

Measured confidence
In daily use · Hotel Divinus
We’re not just department heads — we’re the leaders of Hotel Divinus. That takes a comprehensive “helicopter view” that shows where we stand and which direction to take.

For revenue manager Rita Toronyi, the daily Peaqplus review starts with the forecast, then moves to 1- and 7-day pickup and channel mix. The full routine takes five to ten minutes.

József Márics
Managing Director · Hotel Divinus, Debrecen
Read the Hotel Divinus story →
01
The forecast you actually edit

Build it your way. Keep every version.

Choose the workflow that matches the hotel: segment-level, daily, or a segment-by-day combination. Revenue is calculated from pickup room nights and ADR, while the final committed forecast remains a human decision.

Each committed version stays attached to the month. From the second version onward, every change carries a reason — so the GM and owner can see not only what moved, but why.

The editor workflow
  • Five statuses — Draft (editable) · Committed (visible everywhere) · Locked (month-end frozen) · Superseded (a newer version replaces it) · Expired draft (no commit before month-end)
  • Autosave every 30 seconds — nothing lost; if two people edit the same forecast, the platform warns instead of silently overwriting
  • Optional Smart Forecast Reload — refresh the AI pickup baseline while preserving manual overrides
  • View switcher — Table or Calendar; the calendar makes 30-day pickup edits read at a glance
  • Stale snapshot banner — when fresh OTB lands during a session, the banner offers to refresh the draft to today's data
app.peaqplus.com/forecast/2026-03
SIMULATED HOTEL · FORECAST · MARCH 2026
v3 · DRAFT
v1v2v3
DayOTBLY · SPBudgetSmart F.Final
Mar 05142 / €18.4k128 / €16.2k140 / €18k146146
Mar 06156 / €21.1k149 / €19.8k155 / €21k162160
Mar 07168 / €24.5k158 / €23.1k170 / €23.5k171171
Mar 08124 / €19.2k142 / €22.4k155 / €22k138138
Mar 09118 / €17.8k138 / €21.2k150 / €21.5k132132
Change reason required: Weekend pickup underperformance, lowering Mar 8–9.
02
Forecast Context Bar

The signals stay beside the decision.

The Forecast Context Bar keeps the evidence above the editor: time to arrival, current OTB, Same Point YoY, booking pace, the budget gap and movement from the previous version.

Competitor rates appear when Competitor Intelligence is active; the Smart pickup comparison appears when Pulse AI is active. The core forecasting workflow does not require either add-on.

The eight tiles
  • Time pressure — days left in the month, days to check-in
  • On the books — current OTB for the month
  • Last year, same point — week-position-aware YoY
  • Booking pace — vs last year at the same point in the curve
  • Budget gap — current forecast vs plan, live what-if
  • Competitor rates — relative market position when Competitor Intelligence is active
  • Version movement — how many pickup cells changed vs prior version
  • Smart pickup — the AI baseline vs your manual entry when Pulse AI is active
app.peaqplus.com/forecast/edit · daily · v2 draft
CONTEXT BAR · LIVE
While you edit, the signals refresh.
Time pressure
11 days
remaining in month
On the books
684 RN
−12 RN since yesterday
LY same-point
712 RN
−3.9% vs LY
Booking pace
−4.2%
vs LY at this point
Budget gap
−32 RN
forecast vs plan
Competitor avg*
€152
your position: −4.6%
Version movement
7 cells
changed vs v1
Smart pickup
+9
AI vs your manual entry
Stale snapshot: fresh upload landed at 09:14 — refresh the draft
* Competitor Intelligence required · Smart pickup requires Pulse AI
03
A forecast with a visible foundation

Know where the number came from.

Peaqplus separates three things that are often blurred together: the statistical baseline, the optional AI correction and the accuracy record. You can see each layer independently before a person commits the final forecast.

The statistical baseline and accuracy tracking are included in BI Core. Pulse AI adds the 60-day Smart Forecast Enhanced correction and the written reason behind each adjusted day.

What stays separate
  • Statistical baseline — built per hotel from history, weekday, booking-window position and recent trends
  • Smart Forecast Enhanced — optional daily AI correction using OTB, Same Point YoY, budget, pickup trend and events
  • Accuracy tracking — MAPE, SMAPE and MAE across 7-, 14- and 30-day horizons
  • Clear ownership — the system proposes a baseline; a person commits the forecast
FORECAST RUN · DAILY 5:00 AM
L1
Statistical engine
Per-hotel baseline, rebuilt every night
BI Core
  • ·Built by month, weekday, booking-window position
  • ·Recency-weighted · outlier-filtered · trend-corrected
  • ·Rebuilds overnight — no interruption
L2
AI correction
Smart Forecast Enhanced reads context and adjusts
Pulse AI
  • ·Inputs: OTB · LY same-point · Budget · pickup trend · events
  • ·Per-day reasoning in your language · kept within a sensible band
  • ·Daily refresh · 60-day forecast horizon
L3
Accuracy tracking
Monthly retrospective — how well did it actually work?
BI Core
  • ·Error metrics across 7 / 14 / 30-day horizons
  • ·Raw vs AI side-by-side
  • ·Log never trimmed — long-term trend stays honest
statistical baseline + accuracy in BI Core · AI correction requires Pulse AI
04 — AI assist, with brakes

Start without AI. Add it when it earns a role.

BI Core includes the manual workflow, the statistical forecast levels and accuracy tracking. Pulse AI adds Smart Forecast Enhanced: a daily 60-day correction on top of the hotel-specific baseline, with a written reason for every adjusted day.

Tier
What it uses
Best for
T0
Baseline
Quarterly statistical average
Included in BI Core
T1
Enhanced statistical
Recency-weighted, outlier-filtered, segment-aware
Included in BI Core
T2
AI-corrected
Tier 1 + daily 60-day AI correction
Requires Pulse AI
Built-in safety limits
Corrections stay in bounds
The AI can nudge the statistical baseline, never replace it — every adjustment stays within a fixed, sensible band
Never more rooms than you have
Forecasts can never exceed your physical inventory
No per-call billing
Pulse AI is a flat monthly add-on or part of Pro — AI use is not metered per question
Structured output
The correction follows a fixed, validated format before it reaches the forecast
Overnight refresh
A new Smart Forecast arrives each morning without interrupting the manual workflow
Visible audit trail
The source, timing and reason stay available for review
05
Numbers, not promises

Measure the forecast after reality arrives.

Every month, Peaqplus compares the forecast with the hotel's actual results using MAPE, SMAPE and MAE. The report separates 7-, 14- and 30-day horizons, because a forecast made a week ahead should not be judged like one made a month ahead.

When Pulse AI is active, the same report shows the statistical baseline and the AI-corrected result side by side. The hotel sees the contribution on its own data — no universal accuracy promise.

What's in the monthly report
  • MAPE / SMAPE / MAE for AI corrected vs statistical baseline
  • Per-horizon breakdown (7d / 14d / 30d)
  • Days counted, zero-day exclusions
  • Per-day comparison if you want to dig in
app.peaqplus.com/forecasting/accuracy
SIMULATED EXAMPLE · MAPE
3 tiers · your hotel
T0T1T2 · AI
10%8%6%4%2%W1W2W3W4W5W6W7W8W9W10W11W12
Example display only: your monthly report uses your hotel data and shows the statistical and AI-corrected results side by side.
06
Optional · Pulse AI

Ask the forecast. In your language.

With Pulse AI active, the Forecast Advisor explains why the AI raised or lowered a date, where the next risk sits, which event overlaps with a spike and where the manual forecast differs from the Smart Forecast baseline.

Each answer states how fresh the underlying forecast is. Budget remains the plan, the committed forecast remains the team's position, and Smart Forecast remains the AI suggestion — the three are never presented as the same number.

The Advisor's tools
  • Smart Forecast window — daily AI snapshot, raw-vs-AI delta, freshness timestamp
  • Correction reasoning — three depths: single day (full text) · 2–7 days (detailed) · 8–30 days (summarised)
  • Accuracy trends — raw vs AI side by side, choosable 7 / 14 / 30-day horizons
  • Event lookup — multi-country holidays, festivals, and in-house events on the date range
  • Terminology discipline — "Budget" = the plan only · "forecast" = your manual commitment only · "Smart Forecast" = the AI output only · the Advisor never blurs the three
  • Freshness disclosure — every answer cites when the data was generated; no false certainty
app.peaqplus.com/pulse-chat · Forecast Advisor
🔮
Forecast Advisor
simulated example · Pulse AI add-on
Why is the forecast so high for August 20?
checking the AI's reasoning for Aug 20…

2025-08-20 · 41 room nights (raw: 32, AI: +28%)

National holiday. Last year on this date the pickup was +18; the long weekend pulls neighbouring source markets to a seasonal peak. The Budget is conservative for this day (32 RN); the AI raises it based on the historical pattern.

Freshness: based on the forecast refreshed this morning at 05:00 · generated 2025-04-12 05:03 UTC
Show me the whole week around itWhat other events are coming in August?How accurate was the AI in April?
terminology guard · "Smart Forecast" = AI output (not Budget, not manual commitment)
What you see on every forecast

The number only matters in context.

Compare the committed forecast with what is booked, what was known last year at the same point and what the business planned. Add the AI suggestion only when Pulse AI is active.

01
Actual · OTB

The current on-the-books from your PMS. Live, snapshot-aware.

02
Last year · SP

Week-position-aware YoY — not date-aligned. Thursday week 17 to Thursday week 17.

03
Budget

Your plan, broken to the same granularity as the forecast (segment, daily, or combined).

04
Smart Forecast

The optional Pulse AI suggestion, with the same change-reason audit if you accept it.

The forecast in the working week

One forecast. Different moments of use.

The team can run the full manual workflow in BI Core. The cards marked Pulse AI show the optional layer added by Smart Forecast Enhanced and Forecast Advisor.

01
Morning check

Compare the committed forecast with OTB, pace and budget. Start with the dates where the gap is widening.

Included in BI Core
02
Mid-month update

Create the next version, adjust the dates that changed and attach the reason before committing it.

Included in BI Core
03
Why is this date high?

Ask Forecast Advisor which signals moved the Smart Forecast and how fresh the underlying data is.

Requires Pulse AI
04
Accuracy review

Read the monthly error metrics by forecast horizon and compare the statistical and AI-corrected results when both are active.

Measured on your data
05
Strategic prep

"What events are coming in August?" → multi-country holiday list, local festivals, in-house events. The team prices the affected dates ahead of the curve.

Calendar foresight
06
Refresh the baseline

After fresh PMS data arrives, reload the Smart Forecast while preserving the team's manual overrides.

Requires Pulse AI
Pricing

Start with forecasting in BI Core. Add AI when it is useful.

BI Core starts at €109/month per property and includes the manual forecast workflow, statistical baseline and monthly accuracy tracking. One-time BI setup is €135 and includes 2 hours of team training. Pulse AI adds Smart Forecast Enhanced and Forecast Advisor for €49/month per property with no additional setup fee; it is also included in Pro. Typical BI go-live is 7–14 days, depending on the PMS integration.

Compare plans and add-ons →
Hotel forecasting, in plain terms

The questions teams ask before the demo.

What the forecasting workflow does, what works without AI, and how accuracy is measured.

01
What is hotel forecasting software?

Hotel forecasting software helps a hotel estimate future room nights, occupancy and revenue from current on-the-books reservations, expected pickup and historical patterns. Peaqplus keeps the manual workflow, statistical baseline, committed versions and later accuracy results in one place, so the forecast can support pricing, budget control and management decisions.

02
Can I use Peaqplus forecasting without AI?

Yes. BI Core includes the manual forecast workflow, the T0 and T1 statistical levels, version history and monthly accuracy tracking. Smart Forecast Enhanced and Forecast Advisor are optional Pulse AI features; the final forecast is always committed by a person.

03
How does Peaqplus measure forecast accuracy?

Peaqplus compares the forecast with the hotel's actual results each month using MAPE, SMAPE and MAE across 7-, 14- and 30-day horizons. When Pulse AI is active, the report shows the statistical baseline and AI-corrected result side by side on the hotel's own data.

Signal → Decision → Action → Outcome

Bring the forecast question your team keeps debating.

In a 45–60 minute walkthrough, we use a clearly labelled simulated hotel to build a forecast version, inspect the context behind it and show how monthly accuracy is measured once your own PMS data is live.

The demo is free and carries no commitment. We reply within 1 business day.

Not ready for a demo? Start smaller —5-min revenue check →ROI in 4 numbers →