South Korea Bankruptcies

South Korea · Monthly series · EC-KR-BR

Latest, February 2024

13.0 pts

+8.3% from January 2024

Open interactive chartSouth Korea Bankruptcies in the app

8341-1.009March 2014February 2025
History through February 2024, the forecast path to February 2025 (dashed) and its 80% interval (shaded).

Forecast

Forecast for February 2025: 10.8 pts, with an 80% interval of 1.5 pts to 21.7 pts.

Forecast path. Intervals are shown where available.
PeriodForecast80% low80% high
March 202413.3 pts0.7 pts27.5 pts
April 202414.2 pts7.2 pts22.5 pts
May 202413.3 pts6.0 pts21.5 pts
June 202413.5 pts6.5 pts22.0 pts
July 202412.5 pts5.6 pts20.0 pts
August 202411.8 pts1.7 pts23.1 pts
September 202413.3 pts5.1 pts23.1 pts
October 202415.4 pts9.2 pts23.6 pts
November 202413.7 pts-1.0 pts31.9 pts
December 202414.4 pts2.5 pts30.9 pts
January 202512.1 pts7.5 pts17.7 pts
February 202510.8 pts1.5 pts21.7 pts

Model: Agentic Investor TSFM (foundation model). Forecast generated 2026-11-14.

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
-2%Matches the no-change baseline over 12 tests (12 tests, 5 won)
Direction
62%No clear edge over a coin flip (86 of 139 calls right in 12 tests)
Turning points
69 of 92Anticipated most turns (92 turns in 12 tests, 0 without a turn)
Error vs baseline
2% higherError ratio 1.02; 1.00 is a tie.
Tests won
5 / 12Complete rolling backtests; ties count as no win.
Test period
2012-03-01 to 2024-02-0112 observations ahead per test.
80% band coverage
78%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 13% of the 119 earlier readings since March 2014.

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
February 202413.0 pts
January 202412.0 pts
December 202319.0 pts
November 202314.0 pts
October 202316.0 pts
September 202314.0 pts
August 202312.0 pts
July 202322.0 pts
June 202316.0 pts
May 202320.0 pts
April 202319.0 pts
March 20238.0 pts
February 202311.0 pts
January 202318.0 pts
December 202215.0 pts
November 202213.0 pts
October 202220.0 pts
September 202213.0 pts
August 20229.0 pts
July 20228.0 pts
June 20229.0 pts
May 202212.0 pts
April 202213.0 pts
March 202212.0 pts

Source

Data: public market data feeds.

More from Agentic Investor

Also stored for South Korea