nep-for New Economics Papers
on Forecasting
Issue of 2023‒05‒15
two papers chosen by
Rob J Hyndman
Monash University

  1. A validation workflow for mortality forecasting By Ricarda Duerst; Jonas Schöley; Christina Bohk-Ewald
  2. GDP nowcasting with artificial neural networks: How much does long-term memory matter? By Krist\'of N\'emeth; D\'aniel Hadh\'azi

  1. By: Ricarda Duerst (Max Planck Institute for Demographic Research, Rostock, Germany); Jonas Schöley (Max Planck Institute for Demographic Research, Rostock, Germany); Christina Bohk-Ewald (Max Planck Institute for Demographic Research, Rostock, Germany)
    Abstract: Accurate mortality forecasts are essential for decision makers to plan for changing needs of pension and other social security systems. Researchers have developed a variety of methods with increasing methodological complexity to forecast mortality developments. We introduce a method validation workflow designed for mortality forecasts. The aim of our workflow is to assess the suitability of forecast method depending on the prevailing mortality regime in the country of interest. For our analysis, we apply our workflow to short-term Lee-Carter forecasts for 24 countries to showcase different mortality regimes. We assess Lee-Carter's forecast performance on the life expectancy and lifespan disparity at birth. We show that the mortality regime in the country of interest plays a crucial role for the performance of a forecast method. Thus, our method validation workflow helps researchers to choose an appropriate mortality forecast method.
    Keywords: forecasts, mortality
    JEL: J1 Z0
    Date: 2023
  2. By: Krist\'of N\'emeth; D\'aniel Hadh\'azi
    Abstract: In our study, we apply different statistical models to nowcast quarterly GDP growth for the US economy. Using the monthly FRED-MD database, we compare the nowcasting performance of the dynamic factor model (DFM) and four artificial neural networks (ANNs): the multilayer perceptron (MLP), the one-dimensional convolutional neural network (1D CNN), the long short-term memory network (LSTM), and the gated recurrent unit (GRU). The empirical analysis presents the results from two distinctively different evaluation periods. The first (2010:Q1 -- 2019:Q4) is characterized by balanced economic growth, while the second (2010:Q1 -- 2022:Q3) also includes periods of the COVID-19 recession. According to our results, longer input sequences result in more accurate nowcasts in periods of balanced economic growth. However, this effect ceases above a relatively low threshold value of around six quarters (eighteen months). During periods of economic turbulence (e.g., during the COVID-19 recession), longer training sequences do not help the models' predictive performance; instead, they seem to weaken their generalization capability. Our results show that 1D CNN, with the same parameters, generates accurate nowcasts in both of our evaluation periods. Consequently, first in the literature, we propose the use of this specific neural network architecture for economic nowcasting.
    Date: 2023–04

This nep-for issue is ©2023 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.