Temporal Disaggregation of GDP: When Does Machine Learning Help?

2025/06/17 by Jung, Yonggeun
Economics, Econometrics and Finance · #Econometrics (econ.EM) #FOS: Economics and business #Monetary Policy and Economic Impact

paper · pdf · doi:10.48550/arxiv.2506.14078

openalex publication_date 2025/06/17 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/29

Abstract

We propose a modular framework for temporal disaggregation of quarterly GDP into monthly frequency, in which the regression step accommodates any supervised learning model while Mariano-Murasawa reconciliation enforces quarterly consistency. Comparing Chow-Lin, Elastic Net, XGBoost, and a Multi-Layer Perceptron across four countries, we find that regularization, not nonlinearity, drives the gains: Elastic Net achieves R² = 0.87 for the United States when lagged indicators are included, while nonlinear models cannot overcome the variance cost of small quarterly samples. We formalize this tradeoff through regime-switching bias and ridge-regularization results.

Citations

• High-Dimensional Conditionally Gaussian State Space Models with Missing Data
• How is Machine Learning Useful for Macroeconomic Forecasting?
• A Unified Approach to Interpreting Model Predictions
• Adam: A Method for Stochastic Optimization
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Long Short-Term Memory
• Comparing Predictive Accuracy
• Multilayer feedforward networks are universal approximators
• Testing for unit roots in autoregressive-moving average models of unknown order

Related

• Monthly GDP nowcasting with Machine Learning and Unstructured Data
• Deep Learning for Multi-Country GDP Prediction: A Study of Model Performance and Data Impact
• Machine Learning for Economic Forecasting: An Application to China's GDP Growth
• Nowcasting R&D Expenditures: A Machine Learning Approach
• Harnessing the Potential of Volatility: Advancing GDP Prediction