Home  Journals  Economic Analysis: Theory and Practice  9(552) - 2024 September

Comparative analysis of the predictive power of statistical models of macroeconomic indicators in conditions of permanent crises

Received: 11 April 2024

Received in revised form: 5 August 2024

Accepted: 16 August 2024

Available online: 30 September 2024

Subject Heading: MATHEMATICAL METHODS AND MODELS

JEL Classification: С51, С53, F47

Pages: 1767-1782

https://doi.org/10.24891/ea.23.9.1767

Subject. The article discusses prediction of the state of the economy, the accuracy of forecasts of traditional models during crises, the need to find more effective model specifications to predict macro indicators.
Objectives. The purpose is to carry out a comparative analysis of the predictive ability of ensemble methods in comparison with a set of models, including traditional statistical algorithms and machine learning algorithms.
Methods. The comparative analysis of predictive ability of the models and interpretation of results obtained were performed using a dynamic factor model (DFM), a neural network with long-term short-term memory (LSTM), and integrated gradient methods (IG).
Results. We performed the analysis of predictive ability of the ensemble model to forecast GDP, which combines DFM and LSTM to account for both linear and nonlinear dependencies in the data; the analysis of predictive power of various indicators, which showed that an increase in forecast error is observed for all models except DFM, the ensemble model with an error correction structure, and ARMAX. The obtained results can be used to build models of macroeconomic indicators in order to make strategic decisions by enterprises of various industries operating in a highly uncertain environment.
Conclusions. The combination of DFM and LSTM in the ensemble provides higher accuracy forecasts than LSTM and competitor models, however, with less predictive power than DFM.

Keywords: forecasting model, macroeconomic indicator, dynamic factor model, neural network, ensemble model

References:

1. Bai J., Ng S. Determining the number of factors in approximate factor models. Econometrica, 2002, vol. 70, iss. 1, pp. 191–221. URL: Link
2. Jung R., Richard J.-F., Liesenfeld R. Dynamic Factor Models for Multivariate Count Data: An Application to Stock-Market Trading Activity. Journal of Business and Economic Statistics, 2008, vol. 29(1), pp. 73–85. URL: Link
3. Ponomarev Yu., Pleskachev Yu. [Short-Term GDP Forecasting by Means of Dynamic Factor Model]. Ekonomicheskoe razvitie Rossii = Russia Economic Development, 2018, vol. 25, no. 1, pp. 15–19. URL: Link (In Russ.)
4. Porshakov A.S., Ponomarenko A.A., Sinyakov A.A. [Nowcasting and Short-Term Forecasting of Russian GDP with a Dynamic Factor Model]. Zhurnal Novoi ekonomicheskoi assotsiatsii = Journal of the New Economic Association, 2016, no. 2, pp. 60–76. URL: Link (In Russ.)
5. Jena P.R., Majhi R., Kalli R. et al. Impact of COVID-19 on GDP of major economies: Application of the artificial neural network forecaster. Economic Analysis and Policy, 2021, vol. 69, pp. 324–339. URL: Link
6. Shijun Chen, Xiaoli Han, Yunbin Shen, Chong Ye. Application of Improved LSTM Algorithm in Macroeconomic Forecasting. Computational Intelligence and Neuroscience, 2021, vol. 20. URL: Link
7. Longo L., Riccaboni M., Rungi A. A neural network ensemble approach for GDP forecasting. Journal of Economic Dynamics & Control, 2022, vol. 134, no. 104278. URL: Link
8. Mariano R., Murasawa Y. A new coincident index of business cycles based on monthly and quarterly series. Journal of Applied Econometrics, 2003, vol. 18(4), pp. 427–443. URL: Link
9. Stock J., Watson M. Macroeconomic forecasting using diffusion indexes. Journal of Business and Economic Statistics, 2002, vol. 20, iss. 2, pp 147–162. URL: Link
10. Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, vol. 9, iss. 8, pp. 1735–1780. URL: Link
11. Clark T.E., McCracken M.W. Averaging Forecasts from VARs with Uncertain Instabilities. Journal of Applied Econometrics, 2010, vol. 25(1), pp. 291–311. URL: Link
12. Chernis T., Sekkel R. A dynamic factor model for nowcasting Canadian GDP growth. Empirical Economics, 2017, vol. 53(4), pp. 217–234. URL: Link
13. Ba Chu, Shafiullah Qureshi. Comparing Out-of-Sample Performance of Machine Learning Methods to Forecast U.S. GDP Growth. Computational Economics, 2023, vol. 62, pp. 1567–1609. URL: Link
14. Ahmed N.K., Atiya A.F., Gayar N.E., El-Shishiny H. An empirical comparison of machine learning models for time series forecasting. Econometric Reviews, 2010, vol. 29, iss. 5-6, pp. 594–621. URL: Link
15. Richardson A., Van Florenstein Mulde T., Vehbi T. Nowcasting GDP using machine-learning algorithms: A real-time assessment. International Journal of Forecasting, 2021, vol. 37, iss. 2, pp. 941–948. URL: Link
16. Teräsvirta T., Van Dijk D., Medeiros M.C. Linear models, smooth transition autoregressions, and neural networks for forecasting macroeconomic time series: A re-examination. International Journal of Forecasting, 2005, vol. 21, iss. 4, pp. 755–774. URL: Link

View all articles of issue

ISSN 2311-8725 (Online)
ISSN 2073-039X (Print)

Journal current issue

Vol. 23, Iss. 10 October 2024

Archive