Thailand Labour Costs

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

+40%Beats the no-change baseline over 7 tests (7 tests, 6 won)

Direction

70%No clear edge over a coin flip (19 of 27 calls right in 7 tests)

Turning points

7 of 9Anticipated most turns (9 turns in 7 tests, 0 without a turn)

Error vs baseline

40% lowerError ratio 0.60; 1.00 is a tie.

Tests won

6 / 7Complete rolling backtests; ties count as no win.

Test period

2019-09-01 to 2026-06-014 observations ahead per test.

80% band coverage

86%Observed outcomes inside the band across all stored test windows.

• Band coverage uses all stored test windows, including model-selection windows when present; it does not determine the confidence label.
• Evaluated 2026-11-15 against the cached history through 2026-06-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.