Romania Tourist Arrivals

Romania · Monthly series · EC-RO-TA

Latest, September 2026

308,521.0 pts

-10.4% from August 2026

Open interactive chartRomania Tourist Arrivals in the app

424K212.7K1307October 2016September 2027
History through September 2026, the forecast path to September 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for September 2027: 320,226.6 pts, with an 80% interval of 236,620.9 pts to 380,650.9 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
October 2026267,770.2 pts252,396.1 pts281,625.9 pts
November 2026213,607.7 pts191,250.2 pts235,047.1 pts
December 2026190,836.0 pts168,805.6 pts213,278.1 pts
January 2027170,461.5 pts146,257.7 pts198,122.9 pts
February 2027171,786.6 pts138,263.6 pts209,574.7 pts
March 2027207,943.4 pts159,941.5 pts254,833.6 pts
April 2027231,565.4 pts188,006.8 pts271,134.2 pts
May 2027286,887.2 pts239,133.8 pts326,167.5 pts
June 2027302,923.5 pts258,459.5 pts339,647.0 pts
July 2027330,806.7 pts247,047.6 pts399,723.4 pts
August 2027348,839.8 pts251,349.9 pts424,000.7 pts
September 2027320,226.6 pts236,620.9 pts380,650.9 pts

Model: Agentic Investor TSFM (foundation model). Forecast generated 2026-11-15.

AI confidence

Supported evidence

The point forecast beat the no-change baseline overall and in a majority of the evaluated tests.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
+61%Beats the no-change baseline over 12 tests (12 tests, 12 won)
Direction
90%Beats a coin flip (129 of 144 calls right in 12 tests)
Turning points
22 of 33Anticipated most turns (33 turns in 12 tests, 0 without a turn)
Error vs baseline
61% lowerError ratio 0.39; 1.00 is a tie.
Tests won
12 / 12Complete rolling backtests; ties count as no win.
Test period
2014-10-01 to 2026-09-0112 observations ahead per test.
80% band coverage
79%Observed outcomes inside the band across all stored test windows.
How this assessment is made

AI confidence describes historical evidence for this forecast, not a probability of being correct. Each backtest fits on data available before its test window. The baseline carries the last value forward. Supported evidence requires at least six complete, non-overlapping tests, an error ratio below 0.90 (rounded to two decimals), and wins in a majority of tests. Ratios from 0.90 to below 1.10 are on par; 1.10 or above is weak evidence. Inconsistent wins produce mixed evidence. For a selected model, only the recent tests excluded from model selection determine this label. These are historical simulations using the available data, not a live trading track record; revisions and foundation-model pretraining can limit how closely they reproduce a past decision. Past performance can change.

Replay past tests

Model comparison

Comparison pendingA new ticker first receives its serving model's forecast and evaluation. An eligible nightly batch can compare both candidates, subject to call budgets and retry limits.

Reading

It is above 94% of the 119 earlier readings since October 2016.

Written from the figures by a fixed template; no AI model is involved.

Recent history (24 observations)
The 24 most recent observations, newest first.
PeriodValue
September 2026308,521.0 pts
August 2026344,443.0 pts
July 2026315,174.0 pts
June 2026272,202.0 pts
May 2026278,163.0 pts
April 2026183,321.0 pts
March 2026169,202.0 pts
February 2026143,814.0 pts
January 2026144,893.0 pts
December 2025198,602.0 pts
November 2025190,904.0 pts
October 2025253,097.0 pts
September 2025273,744.0 pts
August 2025298,146.0 pts
July 2025261,886.0 pts
June 2025248,562.0 pts
May 2025239,462.0 pts
April 2025186,744.0 pts
March 2025167,397.0 pts
February 2025134,430.0 pts
January 2025134,266.0 pts
December 2024157,107.0 pts
November 2024174,053.0 pts
October 2024215,830.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Romania