Latvia 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

+27%Beats the no-change baseline over 11 tests (11 tests, 10 won)

Direction

80%Beats a coin flip (106 of 132 calls right in 11 tests)

Turning points

63 of 76Anticipated most turns (76 turns in 11 tests, 0 without a turn)

Error vs baseline

27% lowerError ratio 0.73; 1.00 is a tie.

Tests won

10 / 11Complete rolling backtests; ties count as no win.

Test period

2015-10-01 to 2026-09-0112 observations ahead per test.

80% band coverage

82%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 2026-11-14 against the cached history through 2026-09-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.