Gold / U.S. Dollar
Precious metals · Monthly series · CM-XAUUSD.FOREXCOM
Latest, October 2026
3,875.65 USD (exchange quote)
-6.8% from September 2026
Forecast
Forecast for October 2027: 4,219.97 USD (exchange quote), with an 80% interval of 3,019.73 USD (exchange quote) to 5,420.20 USD (exchange quote).
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| November 2026 | 3,931.65 USD (exchange quote) | 3,643.10 USD (exchange quote) | 4,220.19 USD (exchange quote) |
| December 2026 | 3,957.86 USD (exchange quote) | 3,554.41 USD (exchange quote) | 4,361.31 USD (exchange quote) |
| January 2027 | 3,984.07 USD (exchange quote) | 3,580.79 USD (exchange quote) | 4,387.34 USD (exchange quote) |
| February 2027 | 4,010.28 USD (exchange quote) | 3,602.85 USD (exchange quote) | 4,417.71 USD (exchange quote) |
| March 2027 | 4,036.49 USD (exchange quote) | 3,349.00 USD (exchange quote) | 4,723.98 USD (exchange quote) |
| April 2027 | 4,062.70 USD (exchange quote) | 3,218.97 USD (exchange quote) | 4,906.43 USD (exchange quote) |
| May 2027 | 4,088.91 USD (exchange quote) | 3,442.80 USD (exchange quote) | 4,735.02 USD (exchange quote) |
| June 2027 | 4,115.12 USD (exchange quote) | 2,997.22 USD (exchange quote) | 5,233.03 USD (exchange quote) |
| July 2027 | 4,141.33 USD (exchange quote) | 3,148.25 USD (exchange quote) | 5,134.42 USD (exchange quote) |
| August 2027 | 4,167.54 USD (exchange quote) | 3,039.33 USD (exchange quote) | 5,295.76 USD (exchange quote) |
| September 2027 | 4,193.76 USD (exchange quote) | 3,139.34 USD (exchange quote) | 5,248.17 USD (exchange quote) |
| October 2027 | 4,219.97 USD (exchange quote) | 3,019.73 USD (exchange quote) | 5,420.20 USD (exchange quote) |
AI confidence
Mixed evidenceThe tests show no consistent, material advantage over the no-change baseline.
Model: Exponential smoothing (statistical)
- Accuracy vs naive
- +6%Matches the no-change baseline over 6 tests (6 tests, 4 won)
- Direction
- 72%No clear edge over a coin flip (52 of 72 calls right in 6 tests)
- Turning points
- 0 of 25Anticipated no turn, as the no-change baseline does (25 turns in 6 tests, 0 without a turn)
- Error vs baseline
- 6% lowerError ratio 0.94; 1.00 is a tie.
- Tests won
- 4 / 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.
- 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.
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
5 of 5 models evaluatedModels are selected on older tests and evaluated on separate recent tests. All four classes completed their backtests.
Models tested
Exponential smoothing scored lowest on the 6 older tests (1.00) and was chosen. The 6 recent tests played no part in the choice and give its grade (0.94). 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: Statistical, Foundation model, Machine learning, Neural network.
| Model | Class and compute | Older tests | Recent tests | Role |
|---|---|---|---|---|
| Exponential smoothing (statistical) | Statistical · CPU | 1.00 | 0.94 | Serving |
| Naive forecast (last value held) | Benchmark · CPU | 1.00 | 1.00 | Benchmark |
| State-space model, 167M (foundation model) | Foundation model · CPU | 1.06 | 0.88 | Tested |
| Agentic Investor TSFM (foundation model) | Foundation model · CPU | 1.10 | 1.03 | Tested |
| Gradient-boosted trees (machine learning) | Machine learning · CPU | 1.38 | 0.96 | Tested |
| Hierarchical neural network (neural network) | Neural network · CPU | 1.77 | 1.19 | Tested |
Reading
It is above 90% of the 119 earlier readings since November 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| October 2026 | 3,875.65 USD (exchange quote) |
| September 2026 | 4,157.68 USD (exchange quote) |
| August 2026 | 4,448.10 USD (exchange quote) |
| July 2026 | 4,043.21 USD (exchange quote) |
| June 2026 | 4,007.41 USD (exchange quote) |
| May 2026 | 4,540.17 USD (exchange quote) |
| April 2026 | 4,622.43 USD (exchange quote) |
| March 2026 | 4,668.90 USD (exchange quote) |
| February 2026 | 5,279.20 USD (exchange quote) |
| January 2026 | 4,894.33 USD (exchange quote) |
| December 2025 | 4,319.38 USD (exchange quote) |
| November 2025 | 4,217.99 USD (exchange quote) |
| October 2025 | 4,002.40 USD (exchange quote) |
| September 2025 | 3,859.01 USD (exchange quote) |
| August 2025 | 3,448.26 USD (exchange quote) |
| July 2025 | 3,289.84 USD (exchange quote) |
| June 2025 | 3,302.96 USD (exchange quote) |
| May 2025 | 3,289.24 USD (exchange quote) |
| April 2025 | 3,288.45 USD (exchange quote) |
| March 2025 | 3,123.77 USD (exchange quote) |
| February 2025 | 2,857.86 USD (exchange quote) |
| January 2025 | 2,798.82 USD (exchange quote) |
| December 2024 | 2,624.51 USD (exchange quote) |
| November 2024 | 2,650.59 USD (exchange quote) |
Source
Data: public market data feeds.
More from Agentic Investor
- Open Gold / U.S. Dollar in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators