Sudan Current Account
Sudan · Quarterly series · EC-SD-CA
Latest, Q4 2022
-1.75B USD
-86.3M USD from Q3 2022
Forecast
Forecast for Q4 2023: -1.38B USD, with an 80% interval of -2.94B USD to 336.4M USD.
| Period | Forecast | 80% low | 80% high |
|---|---|---|---|
| Q1 2023 | -1.29B USD | -1.94B USD | -441.0M USD |
| Q2 2023 | -1.16B USD | -1.85B USD | -400.3M USD |
| Q3 2023 | -1.28B USD | -2.32B USD | -124.0M USD |
| Q4 2023 | -1.38B USD | -2.94B USD | 336.4M USD |
AI confidence
Supported evidenceThe 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
- +27%Beats the no-change baseline over 8 tests (8 tests, 6 won)
- Direction
- 75%No clear edge over a coin flip (24 of 32 calls right in 8 tests)
- Turning points
- 6 of 13Anticipated some turns (13 turns in 8 tests, 0 without a turn)
- Error vs baseline
- 27% lowerError ratio 0.73; 1.00 is a tie.
- Tests won
- 6 / 8Complete rolling backtests; ties count as no win.
- Test period
- 2015-03-01 to 2022-12-014 observations ahead per test.
- 80% band coverage
- 94%Observed outcomes inside the band across all stored test windows.
- Band coverage uses all stored test windows, including model-selection windows when present; it does not determine the confidence label.
- The 80% band held more than expected outcomes; interpret its width with care.
- Evaluated 2026-11-15 against the cached history through 2022-12-01.
- This is an evaluation of the serving model; it does not establish a winner across four model classes.
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.
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 5% of the 39 earlier readings since Q1 2013.
Recent history (24 observations)
| Period | Value |
|---|---|
| Q4 2022 | -1.75B USD |
| Q3 2022 | -1.67B USD |
| Q2 2022 | -425.0M USD |
| Q1 2022 | -598.4M USD |
| Q4 2021 | -500.2M USD |
| Q3 2021 | -516.5M USD |
| Q2 2021 | -971.2M USD |
| Q1 2021 | -632.2M USD |
| Q4 2020 | -2.25B USD |
| Q3 2020 | -1.05B USD |
| Q2 2020 | -1.05B USD |
| Q1 2020 | -1.48B USD |
| Q4 2019 | -1.68B USD |
| Q3 2019 | -2.00B USD |
| Q2 2019 | -732.4M USD |
| Q1 2019 | -801.4M USD |
| Q4 2018 | -1.55B USD |
| Q3 2018 | -1.25B USD |
| Q2 2018 | -877.7M USD |
| Q1 2018 | -993.9M USD |
| Q4 2017 | -1.74B USD |
| Q3 2017 | -1.40B USD |
| Q2 2017 | -878.0M USD |
| Q1 2017 | -820.0M USD |
Source
Data: public market data feeds.
More from Agentic Investor
- Open Sudan Current Account in the app: the interactive chart and a fresh forecast
- World and commodity series: every stored series
- Vietnam indicators