LaplaceTerminal

Aluminum Futures

Industrial metals · Monthly series · COMEX:ALI1!

Latest, October 2026

3,167.50 USD (exchange quote)

-4.1% from September 2026

Recent history

The 24 most recent observations, newest first.
PeriodValue
October 20263,167.50 USD (exchange quote)
September 20263,303.25 USD (exchange quote)
August 20263,406.75 USD (exchange quote)
July 20263,364.25 USD (exchange quote)
June 20263,258.00 USD (exchange quote)
May 20263,651.75 USD (exchange quote)
April 20263,431.25 USD (exchange quote)
March 20263,389.75 USD (exchange quote)
February 20263,077.50 USD (exchange quote)
January 20263,090.75 USD (exchange quote)
December 20252,972.25 USD (exchange quote)
November 20252,844.75 USD (exchange quote)
October 20252,862.25 USD (exchange quote)
September 20252,622.00 USD (exchange quote)
August 20252,529.50 USD (exchange quote)
July 20252,493.00 USD (exchange quote)
June 20252,563.00 USD (exchange quote)
May 20252,364.75 USD (exchange quote)
April 20252,318.25 USD (exchange quote)
March 20252,475.75 USD (exchange quote)
February 20252,582.00 USD (exchange quote)
January 20252,588.00 USD (exchange quote)
December 20242,546.50 USD (exchange quote)
November 20242,588.50 USD (exchange quote)

Forecast

Forecast for October 2027: 2,898.21 USD (exchange quote), with an 80% interval of 1,759.02 USD (exchange quote) to 4,155.18 USD (exchange quote).

Forecast path with the 80% interval.
PeriodForecast80% low80% high
November 20263,144.94 USD (exchange quote)2,972.01 USD (exchange quote)3,325.23 USD (exchange quote)
December 20263,124.66 USD (exchange quote)2,805.37 USD (exchange quote)3,447.64 USD (exchange quote)
January 20273,104.04 USD (exchange quote)2,784.38 USD (exchange quote)3,421.91 USD (exchange quote)
February 20273,079.09 USD (exchange quote)2,403.32 USD (exchange quote)3,747.08 USD (exchange quote)
March 20273,055.15 USD (exchange quote)1,701.11 USD (exchange quote)4,418.47 USD (exchange quote)
April 20273,031.71 USD (exchange quote)1,558.22 USD (exchange quote)4,531.92 USD (exchange quote)
May 20273,006.82 USD (exchange quote)1,737.80 USD (exchange quote)4,285.60 USD (exchange quote)
June 20272,981.21 USD (exchange quote)1,681.38 USD (exchange quote)4,298.97 USD (exchange quote)
July 20272,957.11 USD (exchange quote)1,979.92 USD (exchange quote)3,957.53 USD (exchange quote)
August 20272,935.29 USD (exchange quote)2,048.00 USD (exchange quote)3,875.57 USD (exchange quote)
September 20272,918.34 USD (exchange quote)1,446.28 USD (exchange quote)4,478.64 USD (exchange quote)
October 20272,898.21 USD (exchange quote)1,759.02 USD (exchange quote)4,155.18 USD (exchange quote)

Model: Timestral (foundation model). Forecast generated 2026-11-04.

Accuracy: On par with the naive forecast, more accurate in 1 of 6 test years. Its errors were 1.08 times those of the naive forecast (MASE). The 80% band held 81% of outcomes. The naive forecast keeps the latest value for every future period (a random walk).

AI confidence

Mixed evidence

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

Model: Timestral (foundation model)

Error vs baseline
8% higherError ratio 1.08; 1.00 is a tie.
Tests won
1 / 6Complete recent tests excluded from model selection; ties count as no win.
Test period
2020-11-01 to 2026-10-0112 observations ahead per test.
80% band coverage
81%Observed outcomes inside the band across all stored test windows.
How this assessment is made

AI confidence describes historical evidence for this forecast, not a probability of being correct. Each backtest fits on data available before its test window. The baseline carries the last value forward. Supported evidence requires at least six complete, non-overlapping tests, an error ratio below 0.90 (rounded to two decimals), and wins in a majority of tests. Ratios from 0.90 to below 1.10 are on par; 1.10 or above is weak evidence. Inconsistent wins produce mixed evidence. For a selected model, only the recent tests excluded from model selection determine this label. These are historical simulations using the available data, not a live trading track record; revisions and foundation-model pretraining can limit how closely they reproduce a past decision. Past performance can change.

Replay past tests

Model comparison

4 of 4 models evaluatedModels are selected on older tests and evaluated on separate recent tests. All four classes completed their backtests.

Models tested

Timestral scored lowest on the 3 older tests (0.93) and was chosen. The 6 recent tests played no part in the choice and give its grade (1.08). The search for a model that beats the naive forecast on both sets of tests goes on. Scores are MASE: a model's errors divided by the naive forecast's, so 1 is a tie.

4 model classes completed the tests: Foundation model, Statistical, Machine learning, Neural network.

Every model tested on this series.
ModelClass / libraryOlder testsRecent testsRole
Timestral (foundation model)Foundation model · Timestral · GPU0.931.08Serving
Naive forecast (last value held)Benchmark · CPU1.001.00Benchmark
AutoETS (statistical)Statistical · StatsForecast · CPU1.021.00Tested
CatBoost (machine learning)Machine learning · MLForecast · CPU1.291.21Tested
N-HiTS (neural network)Neural network · NeuralForecast · CPU1.322.20Tested

Reading

Aluminum Futures was 3,167.50 USD (exchange quote) in October 2026: -4.1% from September 2026 and +10.7% from October 2025. It is above 92% of the 119 earlier readings since November 2016.

The Timestral forecast puts it at 2,898.21 USD (exchange quote) in October 2027, -8.5% from the latest, with an 80% band from 1,759.02 USD (exchange quote) to 4,155.18 USD (exchange quote). It is on par with the naive forecast: its past errors were 1.08 times as large, and it was more accurate in 1 of 6 test years. The 80% band held 81% of outcomes. The naive forecast keeps the latest value for every future period (a random walk).

Written from the figures by a fixed template; no AI model is involved.

Source

Data: COMEX feed via TradingView.

More from Laplace Terminal

Also stored for Industrial metals