Serbia Steel Production

Serbia · Monthly series · EC-RS-SP

Latest, December 2020

118,700.0 pts

-1.9% from November 2020

Open interactive chartSerbia Steel Production in the app

189.1K94.55K0January 2011December 2021
History through December 2020, the forecast path to December 2021 (dashed) and its 80% interval (shaded).

Forecast

Forecast for December 2021: 117,541.0 pts, with an 80% interval of 75,152.1 pts to 157,345.9 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
January 2021118,430.5 pts93,143.0 pts140,115.7 pts
February 2021118,452.9 pts101,474.8 pts134,498.0 pts
March 2021118,308.3 pts88,011.2 pts148,465.5 pts
April 2021118,155.7 pts78,669.0 pts157,405.9 pts
May 2021118,127.4 pts75,025.2 pts160,729.1 pts
June 2021117,980.1 pts76,963.2 pts158,149.7 pts
July 2021117,840.4 pts90,335.7 pts145,002.5 pts
August 2021117,819.1 pts75,485.0 pts158,765.1 pts
September 2021117,695.4 pts81,297.8 pts152,597.9 pts
October 2021117,628.1 pts87,122.2 pts146,490.6 pts
November 2021117,607.9 pts85,277.7 pts148,329.7 pts
December 2021117,541.0 pts75,152.1 pts157,345.9 pts

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

AI confidence

Mixed evidence

The tests show no consistent, material advantage over the no-change baseline.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive
-3%Matches the no-change baseline over 11 tests (11 tests, 6 won)
Direction
61%No clear edge over a coin flip (76 of 124 calls right in 11 tests)
Turning points
6 of 58Anticipated some turns (58 turns in 11 tests, 0 without a turn)
Error vs baseline
3% higherError ratio 1.03; 1.00 is a tie.
Tests won
6 / 11Complete rolling backtests; ties count as no win.
Test period
2010-01-01 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 65% 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 2020118,700.0 pts
November 2020121,000.0 pts
October 2020123,800.0 pts
September 2020119,600.0 pts
August 2020115,200.0 pts
July 2020114,500.0 pts
June 2020117,000.0 pts
May 2020114,600.0 pts
April 2020109,100.0 pts
March 2020131,300.0 pts
February 2020135,700.0 pts
January 2020135,200.0 pts
December 2019157,800.0 pts
November 2019153,500.0 pts
October 2019159,700.0 pts
September 2019177,600.0 pts
August 2019111,600.0 pts
July 2019136,200.0 pts
June 2019170,700.0 pts
May 2019184,900.0 pts
April 2019176,900.0 pts
March 2019183,700.0 pts
February 2019140,500.0 pts
January 2019176,300.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for Serbia