IMF-传统计量经济学模型与机器学习算法的GDP预测性能：模拟和案例研究（英）

GDP Nowcasting Performance of Traditional Econometric Models vs Machine-Learning Algorithms: Simulation and Case Studies Klakow Akepanidtaworn and Korkrid Akepanidtaworn WP/25/252 IMF Working Papers describe research in progress by the author(s) and are published to elicit comments and to encourage debate. The views expressed in IMF Working Papers are those of the author(s) and do not necessarily represent the views of the IMF, its Executive Board, or IMF management. 2025 DEC* “We would like to sincerely thank Andy Berg, John McDermott, Paul Cashin, Karim Barhoumi, Michal Andrle, Yunhui Zhao,Jiaxiong Yao, Felix Simione, Hany Abdel-Latif, and Iyke Maduako for their valuable comments, data, and insightful suggestions.Any remaining errors are our own. © 2025 International Monetary Fund WP/25/252IMF Working Paper Institute For Capacity Development GDP Nowcasting Performance of Traditional Econometric Models vs Machine-Learning Algorithms: Simulation and Case Studies Prepared by Klakow Akepanidtaworn and Korkrid Akepanidtaworn Authorized for distribution by Natan Epstein December 2025 IMF Working Papers describe research in progress by the author(s) and are published to elicit comments and to encourage debate. The views expressed in IMF Working Papers are those of the author(s) and do not necessarily represent the views of the IMF, its Executive Board, or IMF management. ABSTRACT: Are Machine Learning (ML) algorithms superior to traditional econometric models for GDP nowcasting in a time series setting? Based on our evaluation of all models from both classes ever used in nowcasting across simulation and six country cases, traditional econometric models tend to outperform ML algorithms. Among the ML algorithms, linear ML algorithm – Lasso and Elastic Net – perform best in nowcasting, even surpassing traditional econometric models in cases of long GDP data and rich high-frequency indicators. Among the traditional econometric models, the Bridge and Dynamic Factor deliver the strongest empirical results, while Three-Pass Regression Filter performs well in our simulation. Due to the relatively short length of GDP series, complex and non-linear ML algorithms are prone to overfitting, which compromises their out-of-sample performance. JEL Classification Numbers: C52, C53, C55, C32 Keywords: Nowcasting; Machine Learning; Forecast evaluation; Real-time data Author’s E-Mail Address: kakepanidtaworn@imf.org, korkrid.akepanidtaworn@microsoft.com WORKING PAPERS GDP Nowcasting Performance of Traditional Econometric Models vs Machine-Learning Algorithms: Simulation and Case Studies Prepared by Klakow Akepanidaworn, and Korkid Akepanidtaworn IMF WORKING PAPERS GDP Nowcasting Performance of Traditional Econometric Models vs Machine-Learning Algorithms: Simulation and Case StudiesINTERNATIONAL MONETARY FUND 2 Contents Glossary ...............................................................................................................................................