Construction spending · United States
United States construction spending forecast
Total construction spending (USD billions, seasonally adjusted annual rate)
Model run: Oct 2, 2026 · TimesFM 2.5
3 months forecast · Nov 2026
$2,219B
Median forecast · p10-p90: $2,177B to $2,254B
6 months forecast · Feb 2027
$2,220B
Median forecast · p10-p90: $2,155B to $2,274B
12 months forecast · Aug 2027
$2,219B
Median forecast · p10-p90: $2,115B to $2,336B
Latest observed: $2,203B · Aug 2026
Choose a horizon
The median and range update together.
History & forecast
White: observed history. Blue: forecast median. Shaded: p10-p90 model range.
All values in USD billions, seasonally adjusted annual rate
Model validation
| Horizon | Tests | Model errorModel | No-change errorNo change | Band coverageCoverage |
|---|---|---|---|---|
| 3 months | 58 | $30B | $37B | 75.9% |
| 6 months | 55 | $56B | $68B | 76.4% |
| 12 months | 49 | $98B | $122B | 77.6% |
In these tests the model had lower average error than a no-change forecast at all 3 horizons. Rolling backtests of this model on the latest revised history; overlapping forecast errors are not independent. The p10-p90 band is a model range, not a calibrated guarantee. Methodology · Forecast audit
Evidence & context
Source data
Source & observed data
| Date | Value | Change |
|---|---|---|
| Aug 2026 | $2,203B | +0.85% |
| Jul 2026 | $2,184B | −0.13% |
| Jun 2026 | $2,187B | +0.87% |
| May 2026 | $2,168B | +0.01% |
| Apr 2026 | $2,168B | −1.42% |
| Mar 2026 | $2,199B | +0.44% |
| Feb 2026 | $2,190B | −0.27% |
| Jan 2026 | $2,196B | −0.92% |
| Dec 2025 | $2,216B | −0.21% |
| Nov 2025 | $2,221B | −0.91% |
| Oct 2025 | $2,241B | −0.21% |
| Sep 2025 | $2,246B | +0.17% |
Sources & limits
Source: U.S. Census Bureau · VIP-AXXXX-T-US-SA. Methodology · Forecast audit
Historical context
Outside the model
What could change this forecast?
A small, dated reading list. TimesFM sees the data series, not these stories. This context is not a trading signal.
No recent item selected for this series. We would rather leave this quiet than fill it with a weak match.
Selected for relevance, not a claim of causation. Source dates stay visible. Original reporting remains with its publisher.