United States Gross Fixed Capital Formation

United States · Quarterly series · EC-US-GFCF

Latest, Q3 2026

4.75T USD

+2.3% from Q2 2026

Open interactive chartUnited States Gross Fixed Capital Formation in the app

5.085T3.235T1.385TQ4 1996Q3 2027
History through Q3 2026, the forecast path to Q3 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for Q3 2027: 4.93T USD, with an 80% interval of 4.75T USD to 5.08T USD.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
Q4 20264.80T USD4.72T USD4.88T USD
Q1 20274.84T USD4.71T USD4.97T USD
Q2 20274.89T USD4.66T USD5.08T USD
Q3 20274.93T USD4.75T USD5.08T USD

Model: Agentic Investor TSFM (foundation model). Forecast generated 2026-11-14.

AI confidence

Needs refresh

The data refresh is due. Confidence will be reassessed against the refreshed history.

Model: Agentic Investor TSFM (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

Agentic Investor TSFM scored lowest on the 2 older tests (1.18) and was chosen. The 6 recent tests played no part in the choice and give its grade (0.61). 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, Neural network, Machine learning. Previous model roster.

Every model tested on this series.
ModelClass and computeOlder testsRecent testsRole
Naive forecast (last value held)Benchmark · CPU1.001.00Benchmark
Agentic Investor TSFM (foundation model)Foundation model · CPU1.180.61Serving
Exponential smoothing (statistical)Statistical · CPU1.230.60Tested
Hierarchical neural network (neural network)Neural network · CPU1.241.07Tested
Gradient-boosted trees (machine learning)Machine learning · CPU1.300.52Tested
State-space model, 167M (foundation model)Foundation model · CPU1.310.49Tested

Uses ci-proto, released by Continuous Intelligence. Continuous Intelligence does not endorse or approve this product or service. (ci-proto is shown as State-space model, 167M.)

Reading

That is the highest of the 40 readings since Q4 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
Q3 20264.75T USD
Q2 20264.65T USD
Q1 20264.56T USD
Q4 20254.49T USD
Q3 20254.48T USD
Q2 20254.46T USD
Q1 20254.41T USD
Q4 20244.33T USD
Q3 20244.33T USD
Q2 20244.29T USD
Q1 20244.28T USD
Q4 20234.23T USD
Q3 20234.18T USD
Q2 20234.14T USD
Q1 20234.05T USD
Q4 20224.00T USD
Q3 20224.00T USD
Q2 20224.02T USD
Q1 20224.00T USD
Q4 20213.94T USD
Q3 20213.91T USD
Q2 20213.92T USD
Q1 20213.87T USD
Q4 20203.78T USD

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for United States