Swaziland Balance Of Trade

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

+31%Beats the no-change baseline over 8 tests (8 tests, 8 won)

Direction

72%No clear edge over a coin flip (23 of 32 calls right in 8 tests)

Turning points

12 of 17Anticipated most turns (17 turns in 8 tests, 0 without a turn)

Error vs baseline

31% lowerError ratio 0.69; 1.00 is a tie.

Tests won

8 / 8Complete rolling backtests; ties count as no win.

Test period

2018-06-01 to 2026-03-014 observations ahead per test.

80% band coverage

81%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 2026-03-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.