Forecasting economic activity using a neural network in uncertain times: Monte Carlo evidence and application to the German GDP

Arbeitspapier

In this study, we analyzed the forecasting and nowcasting performance of a generalized regression neural network (GRNN). We provide evidence from Monte Carlo simulations for the relative forecast performance of GRNN depending on the data-generating process. We show that GRNN outperforms an autoregressive benchmark model in many practically relevant cases. Then, we applied GRNN to forecast quarterly German GDP growth by extending univariate GRNN to multivariate and mixed-frequency settings. We could distinguish between "normal" times and situations where the time-series behavior is very different from "normal" times such as during the COVID-19 recession and recovery. GRNN was superior in terms of root mean forecast errors compared to an autoregressive model and to more sophisticated approaches such as dynamic factor models if applied appropriately.

Angaben zum Objekt

• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Series: IWH Discussion Papers ; No. 6/2024

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Single Equation Models; Single Variables: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes ; Neural Networks and Related Topics ; Forecasting Models; Simulation Methods
• Thema: forecasting ; neural network ; nowcasting ; time series models

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Holtemöller, Oliver ; Kozyrev, Boris
• Ereignis: Veröffentlichung
• (wer): Halle Institute for Economic Research (IWH)
• (wo): Halle (Saale)
• (wann): 2024

Weitere Informationen

• URN: urn:nbn:de:gbv:3:2-1054615
• Letzte Aktualisierung: 10.03.2025, 11:44 MEZ