Latvia Asylum Applications

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

+19%Beats the no-change baseline over 12 tests (12 tests, 8 won)

Direction

56%No clear edge over a coin flip (76 of 135 calls right in 12 tests)

Turning points

28 of 69Anticipated some turns (69 turns in 12 tests, 0 without a turn)

Error vs baseline

19% lowerError ratio 0.81; 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.

• 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.