Carregando…
Foz do Iguaçu · Ciudad del Este · Puerto IguazúSaturday, July 4, 2026
Foz do Iguaçu · Ciudad del Este · Puerto IguazúSaturday, July 4, 2026
Live observatory of the Triple Frontier
For the destination · visitor intelligence
The border read for the attraction manager. It pairs real visitor behavior (language and intent of questions on Marco Três) with the movement forecast — to plan staffing, hours and bilingual reinforcement with data, not guesswork.
Profile of the arriving visitor
Language of questions
real dataSample: 4 questions (30 days) · starting base · grows with every question
Where they arrive from (flights)
official · ANACarrivals to Foz · ANAC · 2026-05
Top intents and most-pulled content
Most frequent intents
real dataNot enough questions in the period yet — numbers appear as the Host is used.
Most-pulled content
real datawhat's rising in interest — a signal to prep content and operations
Global attention (Wikipedia)
estimateattention measures pre-trip interest, not actual visits · 14-day window
How and when visitors ask — and use of accessible features
Anticipated demand
real data0
while planning (before arriving)
to integrate in the program on-site via QR
Satisfaction
real dataNot enough questions in the period yet — numbers appear as the Host is used.
Peak by day and hour — operations view
Movement today
Alto
Forecast peak this week
Sat · 04/07
Longest queue today at Itaipu
10h
Shortest queue today at Itaipu
8h
estimatehow we calculate the forecast →
4 · Recommended action
estimateSynthesis for the next decision
Suggestion: forecast peak this week: Sat (04/07, Alto) · longest queue today at itaipu ~10h · 75% English → consider opening an extra slot and bilingual staff (English) at the peak.
Accessibility as intelligence
real use of accessible features and languages in the Host
we answer in all 3 languages; real distribution of questions
The fine-grained data stays with the operator
to integrate in the programThe fine-grained data — turnstile, real queue, official visitor nationality and origin via analytics — comes in through Itaipu's Smart CTI integration. This panel is the public intelligence layer that connects to it.
to integrate in the program Site search
Topics suggested by demand
loopwhat the public asks and we don't answer yet — becomes a content priority
No gaps detected yet. When someone asks something the Host can't answer, the topic shows up here automatically.
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 | ✓ |
Out-of-sample validation: the seasonality learned in 2024 predicted 2025 and matched 11 of 12 months (high × low). Compared against Foz Airport passengers (ANAC) — an independent source that is not a model input. Validates the seasonal/weekly PATTERN, not the hour-by-hour count (that isn't public — it's what Smart CTI would integrate). source: ANAC (open data) · cross-checked with ICMBio/PNI and Itaipu → · open source (lib/backtest.ts) →
Forecast accuracy · forecast × actual
1 reports — reports received. The rate appears once forecast and actual coincide on the same day (updates on the next capture).
Forecast (3×/day heuristic) × actual (community “how is it now?” reports, day's modal level). 60-day rolling window — crowd-sourced, not an official count. how we calculate →