United States Weapons Sales
United States · Annual series · EC-US-WES
Latest, 2025
13,980,000,000.0 pts
+2.4% from 2024
Forecast
Forecast for 2028: 13,986,923,520.0 pts, with an 80% interval of 10,109,895,841.0 pts to 17,969,338,165.8 pts.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| 2026 | 13,770,446,848.0 pts | 10,802,149,571.7 pts | 16,805,326,409.3 pts |
| 2027 | 13,936,191,488.0 pts | 10,149,517,268.2 pts | 17,918,079,666.1 pts |
| 2028 | 13,986,923,520.0 pts | 10,109,895,841.0 pts | 17,969,338,165.8 pts |
AI confidence
Needs refreshThe data refresh is due. Confidence will be reassessed against the refreshed history.
Model: State-space model, 167M (foundation model)
- Accuracy vs naive
- n/aNot evaluated
- Direction
- n/aNot evaluated
- Turning points
- n/aNot evaluated
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. An eligible nightly batch can compare both candidates, subject to call budgets and retry limits.
Models tested
State-space model, 167M scored lowest on the 6 older tests (0.95) and was chosen. The 6 recent tests played no part in the choice and give its grade (0.86). That grade beats the naive forecast. 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. Previous model roster.
| Model | Class and compute | Older tests | Recent tests | Role |
|---|---|---|---|---|
| State-space model, 167M (foundation model) | Foundation model · CPU | 0.95 | 0.86 | Serving |
| Agentic Investor TSFM (foundation model) | Foundation model · CPU | 1.00 | 0.93 | Tested |
| Exponential smoothing (statistical) | Statistical · CPU | 1.00 | 1.00 | Tested |
| Naive forecast (last value held) | Benchmark · CPU | 1.00 | 1.00 | Benchmark |
| Gradient-boosted trees (machine learning) | Machine learning · CPU | 1.21 | 1.08 | Tested |
| Hierarchical neural network (neural network) | Neural network · CPU | 1.28 | 1.26 | Tested |
Reading
It is above 89% of the 9 earlier readings since 2016.
Recent history (24 observations)
| Period | Value |
|---|---|
| 2025 | 13,980,000,000.0 pts |
| 2024 | 13,651,000,000.0 pts |
| 2023 | 11,102,000,000.0 pts |
| 2022 | 15,592,000,000.0 pts |
| 2021 | 10,994,000,000.0 pts |
| 2020 | 9,426,000,000.0 pts |
| 2019 | 10,888,000,000.0 pts |
| 2018 | 9,674,000,000.0 pts |
| 2017 | 11,732,000,000.0 pts |
| 2016 | 9,769,000,000.0 pts |
| 2015 | 9,918,000,000.0 pts |
| 2014 | 9,588,000,000.0 pts |
| 2013 | 7,607,000,000.0 pts |
| 2012 | 8,999,000,000.0 pts |
| 2011 | 8,941,000,000.0 pts |
| 2010 | 8,336,000,000.0 pts |
| 2009 | 7,202,000,000.0 pts |
| 2008 | 7,144,000,000.0 pts |
| 2007 | 7,972,000,000.0 pts |
| 2006 | 7,552,000,000.0 pts |
| 2005 | 6,766,000,000.0 pts |
| 2004 | 6,834,000,000.0 pts |
| 2003 | 5,624,000,000.0 pts |
| 2002 | 4,853,000,000.0 pts |
Source
Data: public market data feeds.
More from Agentic Investor
- Open United States Weapons Sales in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators
Also stored for United States
- United States 15 Year Mortgage Rate
- United States 30 Year Mortgage Rate
- United States ADP Employment Change
- United States API Crude Imports
- United States API Crude Oil Stock Change
- United States API Crude Runs
- United States API Cushing Number
- United States API Distillate Stocks
- United States API Gasoline Stocks
- United States API Heating Oil
- United States API Product Imports
- United States Asylum Applications