AgenticInvestor

Silver Futures

Precious metals · Monthly series · COMEX:SI1!

Latest, October 2026

49.28 USD/APZ

-18.6% from September 2026

Open interactive chartSilver Futures in the terminal

Forecast

No forecast is cached this cycle.

AI confidence

No forecast yet

Evidence will appear when a forecast and its backtests are available.

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.

Model comparison

Previous comparisonThe stored comparison uses earlier data or a previous model roster. A new four-model comparison is not scheduled.

Models tested

AutoETS scored lowest on the 6 older tests (0.99) and was chosen. The 6 recent tests played no part in the choice and give its grade (1.00). The search for a model that beats the naive forecast on both sets of tests goes on. These tests predate the latest data. An eligible nightly batch can repeat them. Scores are MASE: a model's errors divided by the naive forecast's, so 1 is a tie.

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

Every model tested on this series.
ModelClass / libraryOlder testsRecent testsRole
AutoETS (statistical)Statistical · StatsForecast · CPU0.991.00Serving
Naive forecast (last value held)Benchmark · CPU1.001.00Benchmark
Timestral (foundation model)Foundation model · Timestral · GPU1.011.02Tested
N-HiTS (neural network)Neural network · NeuralForecast · CPU1.220.85Tested
CatBoost (machine learning)Machine learning · MLForecast · CPU1.440.99Tested

Reading

It is above 91% of the 119 earlier readings since November 2016.

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

Recent history (24 observations)
The 24 most recent observations, newest first.
PeriodValue
October 202649.28 USD/APZ
September 202660.57 USD/APZ
August 202666.99 USD/APZ
July 202657.79 USD/APZ
June 202659.92 USD/APZ
May 202675.88 USD/APZ
April 202674.03 USD/APZ
March 202674.92 USD/APZ
February 202693.29 USD/APZ
January 202678.53 USD/APZ
December 202570.60 USD/APZ
November 202557.16 USD/APZ
October 202548.16 USD/APZ
September 202546.64 USD/APZ
August 202540.72 USD/APZ
July 202536.71 USD/APZ
June 202536.17 USD/APZ
May 202533.03 USD/APZ
April 202532.83 USD/APZ
March 202534.61 USD/APZ
February 202531.50 USD/APZ
January 202532.27 USD/APZ
December 202429.24 USD/APZ
November 202431.11 USD/APZ

Source

Data: COMEX feed via TradingView.

More from Agentic Investor

Also stored for Precious metals