Anticipating Continued Global Fertility Decline via Neural Forecasting

2026-05-22

AI Summary

This study addresses the challenge of accurately forecasting globally declining fertility rates and assessing their long-term trajectories. It proposes NeuralTFR, the first endogenous forecasting framework that integrates recurrent neural networks with multi-quantile regression, leveraging historical panel data from 196 countries to capture demographic momentum through cross-national information sharing and generate empirical prediction intervals. In backtesting over 2009–2023, NeuralTFR achieves lower point forecast errors than both the naive drift method and the United Nations’ BayesTFR model, while demonstrating comparable uncertainty calibration. Projections to 2040 indicate that most countries will transition into low or very low fertility regimes, challenging the prevailing hypothesis of recent widespread stabilization and establishing a new data-driven benchmark for fertility forecasting.

Abstract

The accelerating shift toward low and ultra-low fertility has intensified the debate over whether countries now undergoing rapid decline are approaching stabilization or entering a more persistent low-fertility regime. Existing projection systems answer that question differently because they embed different assumptions about recovery and about the role of external drivers. To provide an empirical benchmark in this debate, we introduce NeuralTFR, an endogenous global forecasting framework based on a recurrent neural network. Drawing on a harmonized panel of historical fertility series from 196 countries and territories, the model pools cross-country information to learn demographic momentum and generate empirical prediction intervals via multi-quantile regression. Evaluated on a held-out period (2009--2023), NeuralTFR achieves lower point-forecast errors than a Naive Drift baseline and BayesTFR, the United Nations' Bayesian Hierarchical Model, while maintaining competitive uncertainty calibration. In forward projections to 2040, NeuralTFR points to broader exposure to low and very low fertility than BayesTFR, suggesting weaker support for near-term stabilization while still falling short of the most severe decline paths predicted by the Global Burden of Disease project.

Problem

• fertility decline
• low fertility
• population forecasting
• demographic projection
• global fertility

Innovation

• Neural forecasting
• Recurrent neural network
• Multi-quantile regression
• Fertility projection
• Demographic momentum