World population · World · 1 year ahead

2026: the model assigns an 80 percent probability to 8,285,853,010 to 8,294,904,994 people

Point estimate 8,291,408,074 people from Holt (exponential smoothing with additive trend), against 8,215,424,893 people observed in 2025. holt beats last_value on out-of-sample MAE by 95.7 percent over 16 cutoffs (minimum 8, margin 5 percent).

ModeledMetric page

Distribution over the history

Fan chart

Solid: observed (people). Dashed and shaded: model point estimates and 80 percent intervals from empirical residual quantiles. Filled dot: the record on this page. Green or red dot: the realised value, inside or outside its interval.

Quantiles: p5 8,282,472,796 · p10 8,285,853,010 · p25 8,287,219,583 · p50 8,288,637,154 · p75 8,290,365,069 · p90 8,294,904,994 · p95 8,296,061,555
Source: empirical quantiles of 12 in-window 1-step residuals, in log space; no normality assumed

The record

Immutable fields

Key: world-population:WLD:1
Id: 636f8078-462d-4674-8a14-456ce86b00e3
Created: 2026-09-07 22:16 UTC
Data cutoff: 2026-09-07 22:16 UTC
Origin: 2025 = 8,215,424,893 (obs 137382)
Target period: 2026 (365 days)
Point: 8,291,408,074 people
Interval: 8,285,853,010 to 8,294,904,994 at 80 percent
Model: holt models_v1.targets_v1
Baseline: last_value
Snapshot: 182d8a2e360f5457d27b73a363632d053130743665eac890d2335b7cbe884875
Data mode: ingested_at
Status: active

Drivers

Statistical association, not causal

Holt (exponential smoothing with additive trend) uses only the target's own history; there are no driver contributions.

Outcome

Not yet realised

The observation for 2026 has not been ingested. The weekly forecast.evaluate job attaches it when it arrives; the record above does not change.

Scenario assumptions

What the forecast takes for granted

No structural break in world-population between the data cutoff and the target period.
The source keeps publishing the series on the same definition; a rebasing or redefinition invalidates the comparison.
The smoothed level and trend at the cutoff persist over the horizon.

Falsifiers

What would show this forecast wrong

If the first published value of world-population (WLD) for 2026 is below 8,285,853,010 people or above 8,294,904,994 people, the 80 percent interval is falsified.
The model assigns a 10 percent probability to a value below 8,285,853,010 people and a 10 percent probability to a value above 8,294,904,994 people; interval misses should occur about one time in five over many forecasts, and a run of misses well above that rate falsifies the calibration.
The point forecast is above the last observed value (8,215,424,893 people); a realised value at or below that level falsifies the direction call.

Competing models

Scorecard for this target and horizon

Model	Status	Cutoffs	MAE	RMSE	Direction	80% coverage	Skill vs last value
Holt (exponential smoothing with additive trend) models_v1.targets_v1	champion	16	3,458,249	4,396,719	100%	50%	95.7%
Drift models_v1.targets_v1	challenger	16	42,147,912	43,232,101	100%	50%	48.1%
Last value models_v1.targets_v1	baseline	16	81,203,544	81,519,344	0%	100%	0.0%
Linear trend models_v1.targets_v1	challenger	16	18,330,381	22,564,954	100%	69%	77.4%
Ridge regression on lags and drivers models_v1.targets_v1	challenger	16	7,231,864	9,955,672	100%	50%	91.1%

Model card

Holt (exponential smoothing with additive trend)

Purpose. Point and 80 percent interval forecasts of world-population (WLD) 1, 2, 5 years ahead. Owner: Forecast Lab (HV 3.0).

Method

Simple exponential smoothing with an additive trend. Level and trend smoothing parameters (alpha 0.95, beta 0.95) are chosen by grid search on one-step-ahead squared error inside the training window. The series is modelled in natural logarithms and transformed back, so intervals are asymmetric in level terms.

Uncertainty

Intervals are empirical: the model is refitted at earlier origins inside the training window, the realised errors at the same horizon are collected, and the interval is the 10th to 90th percentile of those errors around the point forecast. No normality is assumed.

Training and evaluation

Training window: 66 periods, 1960-01-01 to 2025-01-01. Evaluation: rolling-origin backtest over 16 cutoffs using pseudo real-time data (the earliest ingested value per period; no vintage archive exists for this series, so revisions between the cutoff and today are not reproduced).

Known limitations

Structural breaks after the cutoff are not modelled.
Driver contributions are statistical associations, not causal effects.
Promotion to champion requires beating the last-value baseline on out-of-sample MAE by at least 5 percent over the minimum number of cutoffs; otherwise the baseline stays champion.
Retraining: every scheduled forecast.run refits on the data then available; backtests re-run from /admin/forecasts.

Version chain

Supersedes

This is the first record for its key.