AgenticInvestor

Thailand Tourist Arrivals

Thailand · Monthly series · EC-TH-TA

Latest, September 2026

2,000.3 pts

-20.5% from August 2026

Open interactive chartThailand Tourist Arrivals in the app

4.52M2.246M-27.95KOctober 2016September 2027
History through September 2026, the forecast path to September 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for September 2027: 19,940.6 pts, with an 80% interval of 3,605.5 pts to 1,499,188.5 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
October 202615,554.0 pts5,556.2 pts33,545.4 pts
November 202619,660.4 pts2,389.2 pts165,735.6 pts
December 202622,975.3 pts-1,690.5 pts938,693.4 pts
January 202725,111.1 pts2,364.8 pts1,086,266.4 pts
February 202721,587.8 pts-11,056.5 pts2,111,445.3 pts
March 202718,007.7 pts-15,516.3 pts2,100,932.5 pts
April 202721,875.2 pts-6,706.3 pts1,794,002.6 pts
May 202720,003.2 pts-11,264.0 pts2,246,350.9 pts
June 202722,615.1 pts-11,427.5 pts2,662,320.7 pts
July 202726,003.7 pts-27,950.6 pts4,519,966.8 pts
August 202721,909.3 pts-24,428.9 pts4,277,180.4 pts
September 202719,940.6 pts3,605.5 pts1,499,188.5 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
+36%Beats the no-change baseline over 12 tests (12 tests, 8 won)
Direction
88%Beats a coin flip (127 of 144 calls right in 12 tests)
Turning points
31 of 48Anticipated most turns (48 turns in 12 tests, 0 without a turn)
Error vs baseline
36% lowerError ratio 0.64; 1.00 is a tie.
Tests won
8 / 12Complete rolling backtests; ties count as no win.
Test period
2014-10-01 to 2026-09-0112 observations ahead per test.
80% band coverage
80%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 7% 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 20262,000.3 pts
August 20262,515.3 pts
July 20262,545.6 pts
June 20261,841.5 pts
May 20262,346.8 pts
April 20262,368.9 pts
March 20262,775.2 pts
February 20263,263.8 pts
January 20263,277.9 pts
December 20253,370.4 pts
November 20252,914.8 pts
October 20252,573.7 pts
September 20252,235.8 pts
August 20252,583.6 pts
July 20252,610.4 pts
June 20252,322.8 pts
May 20252,266.6 pts
April 20252,547,120.0 pts
March 2025272,046.0 pts
February 20253,119,445.0 pts
January 20253,709,102.0 pts
December 20243,627,441.0 pts
November 20243,150,237.0 pts
October 20242,679,180.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Thailand