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}.
SMQ: forward projections across 6 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, SMQ'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 1 year (it moves withthe target; r = 0.586 over 45 obs).
| Year | Nowcast | Implied by Current account / GDP in |
|---|---|---|
| 2026 | 2.32 | 2025 (-1.6) |
Latest observed-1.1(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | -1.43 | 0.2 | -3.05 | -1.78 – -1.07 |
| 2028 | -1.08 | 1.73 | -3.9 | -1.71 – -0.46 |
| 2030 | -0.74 | 2.9 | -4.37 | -1.56 – 0.08 |
| 2035 | 0.13 | 5.26 | -5.01 | -1.08 – 1.33 |
Blended 1-yr-ahead-0.99· skill-weighted across models
Track record±0.33typical miss · 1 realized · 30% MAPE
Method: linear_trend; lookback 8y; horizon 1y; confidence 80%
Latest observed5.3T(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 4.7T | 5.5T | 4T | 4.5T – 4.9T |
| 2028 | 5.1T | 6.5T | 3.9T | 4.7T – 5.5T |
| 2030 | 5.5T | 7.3T | 4T | 4.9T – 6.2T |
| 2035 | 6.5T | 9T | 4.4T | 5.2T – 7.9T |
Blended 1-yr-ahead5.4T· skill-weighted across models
Track record±564.6bntypical miss · 1 realized · 11% MAPE
Method: weighted_composite; lookback 8y; horizon 1y; confidence 80%
Latest observed2.1(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 3.5 | 12 | -7.9 | 1.25 – 5.75 |
| 2028 | 4.8 | 12 | -10 | 0.77 – 8.83 |
| 2030 | 6.1 | 12 | -10 | 0.71 – 11.49 |
| 2035 | 9.35 | 12 | -10 | 0.91 – 12 |
Blended 1-yr-ahead1.51· skill-weighted across models
Track record±1.4typical miss · 1 realized · 67% MAPE
Method: weighted_composite; lookback 6y; horizon 1y; confidence 80%
Latest observed12k(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 10.7k | 12.6k | 9.1k | 10.3k – 11.1k |
| 2028 | 11.5k | 14.8k | 8.7k | 10.6k – 12.5k |
| 2030 | 12.3k | 16.5k | 8.7k | 10.9k – 13.8k |
| 2035 | 14.4k | 20.3k | 9.2k | 11.4k – 17.4k |
Blended 1-yr-ahead12.1k· skill-weighted across models
Track record±1.3ktypical miss · 1 realized · 11% MAPE
Method: weighted_composite; lookback 8y; horizon 1y; confidence 80%
Latest observed80.6(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 84.32 | 95.82 | 71.04 | 81.2 – 87.43 |
| 2028 | 87.95 | 107.88 | 64.95 | 80.66 – 95.23 |
| 2030 | 91.58 | 117.3 | 61.89 | 80.29 – 102.86 |
| 2035 | 100.65 | 137.04 | 58.67 | 78.95 – 122.35 |
Blended 1-yr-ahead81.22· skill-weighted across models
Track record±3.72typical miss · 1 realized · 5% MAPE
Method: linear_trend; lookback 10y; horizon 1y; confidence 80%
Latest observed439.8m(2026)· IMF DataMapper API
| Year | Baseline | Optimistic | Pessimistic | Conf. band |
|---|---|---|---|---|
| 2026 | 436.7m | 457.4m | 417.6m | 423.2m – 450.3m |
| 2028 | 439.5m | 460.3m | 420.2m | 407m – 472m |
| 2030 | 442.3m | 463.2m | 422.9m | 392.1m – 492.5m |
| 2035 | 449.2m | 470.4m | 429.5m | 356m – 542.4m |
Blended 1-yr-ahead442.4m· skill-weighted across models
Track record±3.1mtypical miss · 1 realized · 1% 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/SMQ · Country page → · Full brief → · API docs
Fit: Real GDP growth ≈ 3.8264 + 0.9422·Current account / GDP. Correlation, not causation.
Led by Real GDP growth by 3 years (it moves inversely tothe target; r = -0.531 over 26 obs).
| Year | Nowcast | Implied by Real GDP growth in |
|---|---|---|
| 2026 | 64.23 | 2023 (1.8) |
| 2027 | 63.05 | 2024 (2.4) |
| 2028 | 62.06 | 2025 (2.9) |
Fit: Govt debt / GDP ≈ 67.7988 + -1.9801·Real GDP growth. Correlation, not causation.
Machine-readable: GET /api/v1/nowcast/country/SMQ?indicator= · API docs
