Double Descent and Benign Overfitting in Macroeconomic Forecasting

TL;DR

This paper investigates double descent and benign overfitting in macroeconomic forecasting, demonstrating how overparameterization can be effectively managed using synthetic data and kernel methods to improve forecast accuracy.

Contribution

It introduces a novel data augmentation approach with synthetic factors, linking overparameterization to kernel ridge regression, and empirically shows improved forecasting performance.

Findings

Double descent risk curves are observed in macroeconomic datasets.

Synthetic data augmentation improves forecast accuracy across series and horizons.

Benign overfitting is explained through kernel construction rather than intrinsic overparameterization.

Abstract

We study double descent and benign overfitting in macroeconomic forecasting. We document that double-descent risk curves arise in standard macroeconomic datasets that are driven by a small number of latent factors, and we characterize when the underlying benign-overfitting mechanism holds. The conditions of Bartlett et al. (2020) are satisfied under the exact factor model and can also hold under the more realistic approximate factor model, provided idiosyncratic variances are not too dispersed across series. Because macroeconomic panels have only moderate dimensions, the overparameterization ratio N/T required by the theory is not naturally available. Our solution is to augment the data with synthetic copies from an estimated factor model and we prove that this strategy converges to a kernel ridge regression with a factor-structured kernel. Using monthly (FRED-MD) and quarterly (FRED-QD) US data, the resulting estimator consistently outperforms the Stock-Watson factor model for point forecasting across all series and horizons, with gains that are pervasive, statistically significant, and increasing with the forecast horizon. Our results suggest that benign overfitting, when it works, succeeds because overparameterization implicitly constructs a well-behaved kernel, not because overparameterization is intrinsically desirable.