Carregando…
Foz do Iguaçu · Ciudad del Este · Puerto IguazúWednesday, August 19, 2026US dollar R$ 5,19₲1.000 R$ 0,86$1.000 R$ 3,47Foz now 21°C cloudy
Foz do Iguaçu · Ciudad del Este · Puerto IguazúWednesday, August 19, 2026US dollar R$ 5,19₲1.000 R$ 0,86$1.000 R$ 3,47Foz now 21°C cloudy
Operator panel · demo
live · 09:13 PM
Who arrives, what they look for and how much movement to expect, to plan staffing and hours with data, not guesswork.
This panel is a public demo with aggregated regional data. The per-client panel, with your attraction's data, reports and alerts, is private: client area · see the offer
Movement now
Baixo
→ steady since 12:10
today's forecast for the border
Peak this week
Sat 22
high movement
staff up and extend hours
Bridge queue
Medium queue
automatic camera reading (AI) · 13 min ago
to Paraguay
Accuracy
92%
11/12 months · ANAC-validated
From ops to data
What the Complex operator raised in pre-incubation, and the data already live. The forecast is validated against ANAC passenger counts.
“Rain, airfare and fuel move the real number, and there's no integrated flow.”
live + programWeather on all 3 sides already feeds the forecast; airfare (ANAC arrivals) and fuel (ANP) are already measured live. Fusing the three into one predicted number: in the program.
“I check the Paraguay queue in the morning: if it's long, the afternoon gets busier.”
liveLeading signal: a long morning queue at the Friendship Bridge → tendency of more afternoon movement. We measure and log it every day (on this page).
“Hotel occupancy misleads: many come for a one-day resort stay and don't circulate.”
liveWe separate REAL movement at the attractions from hotel occupancy, a passenger counts movement, not a visit. The honest airport × Falls ratio is open.
Which language visitors ask in and where the flights come from.
Language of questions
real dataSample: 34 questions (30 days) · starting base · grows with every question
Where they arrive from (flights)
official · ANACWhat they ask most and which content they open most.
Most frequent intents
real dataConfusion points: Queues / timing → Suggested action: Communicate hours and the best time to visit
Most-read content
real dataIs interest in the destination rising or falling, a signal to prep content and operations.
Global attention (Wikipedia)
estimateattention measures pre-trip interest, not actual visits · 14-day window
A long morning queue at the Friendship Bridge tends to anticipate more afternoon movement. We measure and log it every day to confirm the rule with numbers.
Now
hypothesis under validationFriendship Bridge flowing now, no leading signal of an extra afternoon peak.
✓ validating for 46 days (since 05/07) · so far, on 0 of 23 long-queue mornings the measured afternoon movement came in medium/high
morning = traffic at the Friendship Bridge 8-11am · afternoon = traffic on the access roads 2-5pm (GPS traffic measurement, not a people count)
Access-road movement right now, by attraction
real dataHow much movement to expect today and when it peaks.
Best time today, by attraction
| Attraction | Shortest queue | Longest queue |
|---|---|---|
| Falls (BR) | 16h | 14h |
| Itaipu | 16h | 10h |
| Three Frontiers Landmark | 8h | 18h |
estimatehow we calculate the forecast →
Why it looks like this
Today: typical season · no holiday in the three countries · no rain forecast.
Given today's weather, what makes sense to prioritize.
Clear weather → open-air day; indoor ones absorb queues at peak or as plan B:
estimatePrioritize today
Leave for later / plan B
Today's recommendation
estimateSynthesis for the next decision
Suggestion: forecast peak this week: Sat (22/08, Alto) · falls (br): shortest queue ~16h · 35% Spanish · queues / timing → consider opening an extra slot and bilingual staff (Spanish) at the peak.
“Weather changes which attraction fills up: sun for open-air, rain for indoor.”
liveWeather-based redistribution: given today's weather, the panel prioritizes open-air or indoor (further down this page).
“I want to understand behavior and redistribute flow, see where they linger and where space is underused.”
live + programLanguage, intent and most-read content + access-road traffic per attraction already live. Dwell time and point-by-point occupancy (sensor/turnstile): in the program.
“If it works, the wish is to hire and take it to other attractions (Abrajet, Sebrae).”
liveThe offer for the destination is already designed, observatory, flow forecast and AI presence, replicable to any attraction by configuration.
arrivals to Foz · ANAC · 2026-06see all →
Most-asked attractions
34 questions asked before arriving (planning)
Traffic measured on each attraction's arrival road, the slower it is, the more people arriving.
GPS traffic measurement, indicates movement, doesn't count people
Validation against public visitation 2025
| Month | Forecast (2024) | Actual (2025) | Match |
|---|---|---|---|
| Jan | high | high | ✓ |
| Feb | low | low | ✓ |
| Mar | low | low | ✓ |
| Apr | low | low | ✓ |
| May | low | low | ✓ |
| Jun | low | low | ✓ |
| Jul | high | low | ✗ |
| Aug | high | high | ✓ |
| Sep | low | low | ✓ |
| Oct | high | high | ✓ |
| Nov | high | high | ✓ |
| Dec | high | high | ✓ |
We test the forecast against another year's actual: the seasonality learned in 2024 predicted 2025 and matched 11 of 12 months (high × low). Compared against Foz Airport passengers (ANAC), a source independent of the forecast. Validates the seasonal/weekly PATTERN, not the hour-by-hour count (that isn't public). source: ANAC (open data) · cross-checked with ICMBio/PNI and Itaipu → · open source →
Forecast accuracy · forecast × actual
4 reports: reports received. The rate appears once forecast and actual coincide on the same day (updates on the next capture).
Forecast (3×/day, from day, hour and weather) × actual (community “how is it now?” reports, day's modal level). 60-day rolling window, community reports, not an official count. how we calculate →