Temporal Disaggregation of GDP: When Does Machine Learning Help?

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Jung, Yonggeun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915938256814080
author Jung, Yonggeun
author_facet Jung, Yonggeun
contents 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 $R^2 = 0.87$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14078
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporal Disaggregation of GDP: When Does Machine Learning Help?
Jung, Yonggeun
Econometrics
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 $R^2 = 0.87$ 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.
title Temporal Disaggregation of GDP: When Does Machine Learning Help?
topic Econometrics
url https://arxiv.org/abs/2506.14078