United States Housing Starts Single Family

United States · Monthly series · EC-US-HSSF

Latest, September 2026

859,000.0 pts

-4.6% from August 2026

Open interactive chartUnited States Housing Starts Single Family in the app

1.273M980.5K688KOctober 2016September 2027
History through September 2026, the forecast path to September 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for September 2027: 881,038.4 pts, with an 80% interval of 797,543.3 pts to 962,854.0 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
October 2026867,293.8 pts804,417.4 pts931,276.1 pts
November 2026868,654.5 pts764,737.5 pts973,484.9 pts
December 2026870,720.1 pts772,806.7 pts969,073.8 pts
January 2027871,043.9 pts817,093.3 pts924,751.7 pts
February 2027871,526.9 pts707,404.9 pts1,034,768.8 pts
March 2027872,011.4 pts751,638.0 pts992,641.3 pts
April 2027873,398.4 pts767,033.4 pts979,218.9 pts
May 2027875,318.0 pts773,310.3 pts975,396.4 pts
June 2027876,765.4 pts797,226.9 pts954,446.9 pts
July 2027877,793.5 pts773,415.9 pts979,956.7 pts
August 2027879,200.8 pts801,908.5 pts954,474.1 pts
September 2027881,038.4 pts797,543.3 pts962,854.0 pts

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

Comparison pendingA new ticker first receives its serving model's forecast and evaluation. An eligible nightly batch can compare both candidates, subject to call budgets and retry limits.

Reading

It is above 18% of the 119 earlier readings since October 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
September 2026859,000.0 pts
August 2026900,000.0 pts
July 2026875,000.0 pts
June 2026902,000.0 pts
May 2026889,000.0 pts
April 2026914,000.0 pts
March 20261,017,000.0 pts
February 2026923,000.0 pts
January 2026894,000.0 pts
December 2025946,000.0 pts
November 2025929,000.0 pts
October 2025893,000.0 pts
September 2025837,000.0 pts
August 2025873,000.0 pts
July 2025959,000.0 pts
June 2025925,000.0 pts
May 2025945,000.0 pts
April 2025953,000.0 pts
March 2025939,000.0 pts
February 20251,094,000.0 pts
January 20251,002,000.0 pts
December 20241,056,000.0 pts
November 20241,010,000.0 pts
October 2024958,000.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for United States