AgenticInvestor

Taiwan Steel Production

Taiwan · Monthly series · EC-TW-SP

Latest, December 2020

1,700,000.0 pts

+3.0% from November 2020

Open interactive chartTaiwan Steel Production in the app

2.094M1.727M1.36MJanuary 2011December 2021
History through December 2020, the forecast path to December 2021 (dashed) and its 80% interval (shaded).

Forecast

Forecast for December 2021: 1,755,420.6 pts, with an 80% interval of 1,474,610.4 pts to 1,993,759.0 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
January 20211,717,594.8 pts1,593,205.9 pts1,830,009.4 pts
February 20211,602,613.9 pts1,359,773.1 pts1,794,722.3 pts
March 20211,798,608.5 pts1,631,800.9 pts1,942,563.6 pts
April 20211,742,276.8 pts1,575,276.4 pts1,893,786.3 pts
May 20211,777,128.5 pts1,536,734.5 pts1,989,071.9 pts
June 20211,690,963.2 pts1,507,909.3 pts1,858,399.2 pts
July 20211,727,588.5 pts1,553,807.5 pts1,881,678.9 pts
August 20211,714,185.0 pts1,467,857.6 pts1,931,904.4 pts
September 20211,647,480.0 pts1,519,878.1 pts1,754,592.8 pts
October 20211,756,509.5 pts1,468,749.7 pts2,001,918.6 pts
November 20211,695,498.1 pts1,405,106.7 pts1,944,367.3 pts
December 20211,755,420.6 pts1,474,610.4 pts1,993,759.0 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, 10 won)
Direction
69%No clear edge over a coin flip (100 of 144 calls right in 12 tests)
Turning points
92 of 93Anticipated most turns (93 turns in 12 tests, 0 without a turn)
Error vs baseline
15% lowerError ratio 0.85; 1.00 is a tie.
Tests won
10 / 12Complete rolling backtests; ties count as no win.
Test period
2009-01-01 to 2020-12-0112 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 17% of the 119 earlier readings since January 2011.

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 20201,700,000.0 pts
November 20201,650,000.0 pts
October 20201,653,420.0 pts
September 20201,605,000.0 pts
August 20201,625,000.0 pts
July 20201,750,000.0 pts
June 20201,700,000.0 pts
May 20201,744,190.0 pts
April 20201,756,800.0 pts
March 20201,955,860.0 pts
February 20201,767,110.0 pts
January 20201,794,990.0 pts
December 20191,693,390.0 pts
November 20191,650,410.0 pts
October 20191,713,070.0 pts
September 20191,746,210.0 pts
August 20191,854,990.0 pts
July 20191,877,870.0 pts
June 20191,808,670.0 pts
May 20191,934,230.0 pts
April 20191,970,450.0 pts
March 20192,032,080.0 pts
February 20191,682,750.0 pts
January 20191,990,240.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Taiwan