Metal Bulletin Aluminum European Premium Duty-Paid Futures

The tests show no consistent, material advantage over the no-change baseline.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive

-5%Matches the no-change baseline over 7 tests (7 tests, 3 won)

Direction

50%No clear edge over a coin flip (41 of 82 calls right in 7 tests)

Turning points

12 of 29Anticipated some turns (29 turns in 7 tests, 0 without a turn)

Error vs baseline

5% higherError ratio 1.05; 1.00 is a tie.

Tests won

3 / 7Complete rolling backtests; ties count as no win.

Test period

2019-11-01 to 2026-10-0112 observations ahead per test.

80% band coverage

83%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 2026-10-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.