Puerto Rico Unemployed Persons

Puerto Rico · Monthly series · EC-PR-UP

Latest, August 2026

83,000.0 pts

-4.6% from July 2026

Open interactive chartPuerto Rico Unemployed Persons in the app

146K105K64KJune 2016August 2027
History through August 2026, the forecast path to August 2027 (dashed) and its 80% interval (shaded).

Forecast

Forecast for August 2027: 74,839.2 pts, with an 80% interval of 64,601.5 pts to 98,340.8 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
September 202679,258.2 pts72,924.1 pts87,609.6 pts
October 202676,815.6 pts69,537.4 pts88,892.8 pts
November 202675,906.0 pts68,139.1 pts90,688.3 pts
December 202674,881.4 pts67,271.2 pts91,328.8 pts
January 202773,993.7 pts66,304.4 pts91,798.6 pts
February 202773,346.6 pts65,531.3 pts92,406.1 pts
March 202772,631.9 pts65,072.4 pts92,498.5 pts
April 202772,173.1 pts64,691.8 pts93,432.8 pts
May 202772,691.0 pts64,579.5 pts94,857.5 pts
June 202773,836.7 pts64,513.6 pts96,322.5 pts
July 202774,810.5 pts64,563.6 pts97,871.8 pts
August 202774,839.2 pts64,601.5 pts98,340.8 pts

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

AI confidence

Limited evidence

At least 6 complete tests are required; 3 are available.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
n/aToo few tests (3 tests, 6 needed) (3 tests, 1 won)
Direction
n/aToo few tests (3 tests, 6 needed) (19 of 34 calls right in 3 tests)
Turning points
n/aToo few tests (3 tests, 6 needed) (11 turns in 3 tests, 0 without a turn)
Error vs baseline
10% lowerError ratio 0.90; 1.00 is a tie.
Tests won
1 / 3Complete rolling backtests; ties count as no win.
Test period
2023-09-01 to 2026-08-0112 observations ahead per test.
80% band coverage
100%Observed outcomes inside the band across all stored test windows.
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.

Replay past tests

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 50% of the 116 earlier readings since September 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
August 202683,000.0 pts
July 202687,000.0 pts
June 202681,000.0 pts
May 202667,000.0 pts
April 202665,000.0 pts
March 202666,000.0 pts
February 202667,000.0 pts
January 202669,000.0 pts
December 202570,000.0 pts
November 202570,000.0 pts
October 202571,000.0 pts
September 202575,000.0 pts
August 202579,000.0 pts
July 202570,000.0 pts
June 202571,000.0 pts
May 202564,000.0 pts
April 202565,000.0 pts
March 202565,000.0 pts
February 202566,000.0 pts
January 202566,000.0 pts
December 202467,000.0 pts
November 202468,000.0 pts
October 202467,000.0 pts
September 202466,000.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Puerto Rico