Trinidad and Tobago Steel Production

Trinidad and Tobago · Monthly series · EC-TT-SP

Latest, December 2017

0.0 pts

0.0 pts from November 2017

Open interactive chartTrinidad and Tobago Steel Production in the app

62K30.82K-357.1January 2008December 2018
History through December 2017, the forecast path to December 2018 (dashed) and its 80% interval (shaded).

Forecast

Forecast for December 2018: 326.4 pts, with an 80% interval of -202.1 pts to 39,562.1 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
January 2018168.9 pts8.9 pts820.4 pts
February 2018207.0 pts-36.5 pts1,305.0 pts
March 2018240.7 pts-304.2 pts3,516.2 pts
April 2018287.4 pts-357.1 pts6,596.1 pts
May 2018231.3 pts-158.3 pts7,099.2 pts
June 2018199.6 pts-144.1 pts13,355.6 pts
July 2018282.7 pts-49.3 pts13,047.5 pts
August 2018326.2 pts89.2 pts11,098.1 pts
September 2018272.3 pts-159.0 pts29,409.1 pts
October 2018273.6 pts-225.2 pts36,797.9 pts
November 2018245.0 pts-207.7 pts41,173.4 pts
December 2018326.4 pts-202.1 pts39,562.1 pts

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

AI confidence

Supported evidence

The point forecast beat the no-change baseline overall and in a majority of the evaluated tests.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
+15%Beats the no-change baseline over 12 tests (12 tests, 8 won)
Direction
72%No clear edge over a coin flip (93 of 129 calls right in 11 tests)
Turning points
18 of 60Anticipated some turns (60 turns in 12 tests, 0 without a turn)
Error vs baseline
15% lowerError ratio 0.85; 1.00 is a tie.
Tests won
8 / 12Complete rolling backtests; ties count as no win.
Test period
2006-01-01 to 2017-12-0112 observations ahead per test.
80% band coverage
81%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 0% of the 119 earlier readings since January 2008.

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
December 20170.0 pts
November 20170.0 pts
October 20170.0 pts
September 20170.0 pts
August 20170.0 pts
July 20170.0 pts
June 20170.0 pts
May 20170.0 pts
April 20170.0 pts
March 20170.0 pts
February 20170.0 pts
January 20170.0 pts
December 20160.0 pts
November 20160.0 pts
October 20160.0 pts
September 20160.0 pts
August 20160.0 pts
July 20160.0 pts
June 20160.0 pts
May 20160.0 pts
April 20160.0 pts
March 20160.0 pts
February 20160.0 pts
January 201635,000.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Trinidad and Tobago