Hong Kong Unemployed Persons

Hong Kong · Monthly series · EC-HK-UP

Latest, September 2026

155,000.0 pts

+0.7% from August 2026

Open interactive chartHong Kong Unemployed Persons in the app

261.6K181.7K101.8KOctober 2016September 2027
History through September 2026, the forecast path to September 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for September 2027: 153,833.8 pts, with an 80% interval of 134,072.0 pts to 183,257.2 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
October 2026151,279.2 pts147,250.5 pts155,165.9 pts
November 2026145,759.6 pts137,888.9 pts154,195.7 pts
December 2026139,931.6 pts126,460.4 pts156,037.1 pts
January 2027137,360.6 pts124,425.8 pts154,260.7 pts
February 2027137,312.9 pts124,826.1 pts154,026.4 pts
March 2027142,265.3 pts123,536.9 pts167,678.0 pts
April 2027145,267.3 pts122,557.9 pts176,822.7 pts
May 2027146,794.0 pts118,257.5 pts187,349.9 pts
June 2027148,009.4 pts119,313.5 pts190,424.8 pts
July 2027151,860.6 pts121,138.8 pts196,556.3 pts
August 2027154,689.0 pts129,704.7 pts191,144.0 pts
September 2027153,833.8 pts134,072.0 pts183,257.2 pts

Model: Agentic Investor TSFM (foundation model). Forecast generated 2026-11-15.

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 75% 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 2026155,000.0 pts
August 2026153,900.0 pts
July 2026145,700.0 pts
June 2026139,700.0 pts
May 2026141,100.0 pts
April 2026139,200.0 pts
March 2026136,600.0 pts
February 2026134,700.0 pts
January 2026138,400.0 pts
December 2025138,200.0 pts
November 2025144,400.0 pts
October 2025149,600.0 pts
September 2025155,600.0 pts
August 2025151,000.0 pts
July 2025145,000.0 pts
June 2025136,200.0 pts
May 2025135,800.0 pts
April 2025129,400.0 pts
March 2025122,800.0 pts
February 2025111,700.0 pts
January 2025110,100.0 pts
December 2024113,600.0 pts
November 2024119,700.0 pts
October 2024120,700.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Hong Kong