Forecast
Forward projections from the prediction engine — baseline plus an optimistic/pessimistic band and a confidence interval, per macro indicator. These are PROJECTIONS, not observations: generated from observed history, never a guarantee. A country we hold no projections for is shown honestly.
Forecast
Need it as JSON? GET /api/v1/forecast/country/{iso3}.
AFQ: forward projections across 7 macro indicators, horizons 2026, 2028, 2030, 2035. These are projections, not observations — each carries an optimistic/pessimistic band and a confidence interval, anchored against the latest observed value where one is held.
Nowcast
Each indicator nowcast from its strongest leading series — inferable from observations already in hand.
For each indicator, AFQ's strongest leading series is fit by ordinary least squares over their shared observed history, then the leader's already-observed recent values project the target — so the next year or two is inferable from data already in hand. These are nowcasts from a leading correlation: correlation, not causation, and not a guaranteed forecast.
Led by Current account / GDP by 3 years (it moves inversely tothe target; r = -0.683 over 26 obs).
| Year | Nowcast | Implied by Current account / GDP in |
|---|---|---|
| 2026 | 49.7 | 2023 (-1.6) |
Latest observed-1.5(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | -1.93 | -0.37 | -3.49 | -2.28 – -1.58 |
| 2028 | -1.59 | 1.11 | -4.29 | -2.22 – -0.96 |
| 2030 | -1.25 | 2.23 | -4.73 | -2.06 – -0.44 |
| 2035 | -0.4 | 4.52 | -5.32 | -1.56 – 0.77 |
Blended 1-yr-ahead-1.34· skill-weighted across models
Track record±0.43typical miss · 1 realized · 29% MAPE
Method: linear_trend; lookback 8y; horizon 1y; confidence 80%
Latest observed3.7T(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 3.2T | 3.5T | 2.8T | 3.1T – 3.3T |
| 2028 | 3.2T | 3.8T | 2.6T | 2.9T – 3.4T |
| 2030 | 3.2T | 4T | 2.5T | 2.8T – 3.6T |
| 2035 | 3.3T | 4.4T | 2.2T | 2.6T – 3.9T |
Blended 1-yr-ahead3.8T· skill-weighted across models
Track record±491.9bntypical miss · 1 realized · 13% MAPE
Method: weighted_composite; lookback 8y; horizon 1y; confidence 80%
Latest observed4.6(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 5.09 | 10.57 | 0.34 | 4.09 – 6.09 |
| 2028 | 6.45 | 12 | -1.78 | 4.56 – 8.34 |
| 2030 | 7.8 | 12 | -2.82 | 5.14 – 10.47 |
| 2035 | 11.2 | 12 | -3.83 | 6.52 – 12 |
Blended 1-yr-ahead4.7· skill-weighted across models
Track record±0.49typical miss · 1 realized · 11% MAPE
Method: weighted_composite; lookback 6y; horizon 1y; confidence 80%
Latest observed2.4k(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 2.1k | 2.4k | 1.9k | 2k – 2.2k |
| 2028 | 2k | 2.5k | 1.6k | 1.9k – 2.2k |
| 2030 | 2k | 2.6k | 1.4k | 1.7k – 2.2k |
| 2035 | 1.8k | 2.6k | 1k | 1.4k – 2.1k |
Blended 1-yr-ahead2.5k· skill-weighted across models
Track record±316typical miss · 1 realized · 13% MAPE
Method: weighted_composite; lookback 8y; horizon 1y; confidence 80%
Latest observed63.1(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 66.02 | 71.65 | 59.54 | 63.98 – 68.07 |
| 2028 | 70.47 | 80.21 | 59.23 | 65.26 – 75.68 |
| 2030 | 74.92 | 87.49 | 60.41 | 66.41 – 83.42 |
| 2035 | 86.04 | 103.82 | 65.52 | 68.19 – 103.88 |
Blended 1-yr-ahead63.97· skill-weighted across models
Track record±2.92typical miss · 1 realized · 5% MAPE
Method: linear_trend; lookback 10y; horizon 1y; confidence 80%
Latest observed9.3(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 9.44 | 18.63 | -0.41 | 7.25 – 11.63 |
| 2028 | -2.46 | 13.45 | -5 | -5 – 1.18 |
| 2030 | -5 | 15.55 | -5 | -5 – -0.04 |
| 2035 | -5 | 24.06 | -5 | -5 – 2.24 |
Blended 1-yr-ahead8.4· skill-weighted across models
Track record±0.14typical miss · 1 realized · 1% MAPE
Method: exponential_smoothing; lookback 6y; horizon 1y; confidence 80%
Latest observed1.5bn(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 1.5bn | 1.5bn | 1.4bn | 1.4bn – 1.5bn |
| 2028 | 1.5bn | 1.6bn | 1.4bn | 1.4bn – 1.6bn |
| 2030 | 1.5bn | 1.6bn | 1.5bn | 1.4bn – 1.7bn |
| 2035 | 1.6bn | 1.7bn | 1.5bn | 1.3bn – 2bn |
Blended 1-yr-ahead1.5bn· skill-weighted across models
Track record±42.7mtypical miss · 1 realized · 3% MAPE
Method: exponential_smoothing; lookback 10y; horizon 1y; confidence 80%
Reliability badges show each indicator's best model skill— how much it beats a naive last-value forecast, measured out-of-sample on that series' own observed history (backtested one-step-ahead). A track record, not a guarantee of future accuracy.
Generated by the prediction engine (model prediction-engine-v1) on 2026-10-31 from observed history. Projections, not observations — never a guarantee of future values.
Machine-readable: GET /api/v1/forecast/country/AFQ · Country page → · Full brief → · API docs
| 2027 | 49.7 | 2024 (-1.6) |
| 2028 | 51.24 | 2025 (-2.1) |
Fit: Govt debt / GDP ≈ 44.75 + -3.0923·Current account / GDP. Correlation, not causation.
Led by Real GDP growth by 3 years (it moves inversely tothe target; r = -0.614 over 32 obs).
| Year | Nowcast | Implied by Real GDP growth in |
|---|---|---|
| 2026 | 13.55 | 2023 (3.4) |
| 2027 | 13.31 | 2024 (3.5) |
| 2028 | 10.82 | 2025 (4.5) |
Fit: CPI inflation ≈ 22.0161 + -2.4889·Real GDP growth. Correlation, not causation.
Machine-readable: GET /api/v1/nowcast/country/AFQ?indicator= · API docs
