Machine Learning Versus Deep Learning in Macroeconomic Forecasting: A Global GDP Growth Application

Fazale Naeem, Muhammad Naveed, Muhammad Fayez, Santosh Prasad Sah

Abstract

This study compares regularized linear, tree-based ensemble, boosting, and feed-forward neural-network approaches for forecasting country-level annual GDP growth using a global panel covering 213 countries from 2010 to 2023. A chronological out-of-sample evaluation is employed, with models trained on observations through 2021 and tested on 401 country-year observations from 206 countries during 2022–2023. Ridge regression, Random Forest, Histogram-Based Gradient Boosting, AdaBoost, and a multi-layer perceptron (MLP) are evaluated using root mean squared error (RMSE). Ridge regression records the lowest observed test RMSE (5.50), followed by Histogram-Based Gradient Boosting (6.28), Random Forest (6.75), AdaBoost (7.13), and the MLP (8.12). AdaBoost is treated as a classical boosting-based machine-learning method, whereas the MLP serves as the neural-network benchmark. The baseline models use one-year lags, while AdaBoost and the MLP use one-to-three-year lag windows. Consequently, the observed ranking reflects differences in both model specifications and information sets and should not be interpreted as a strictly like-for-like comparison or evidence of statistical superiority. Within this annual panel, predictor set, and 2022–2023 evaluation period, greater model complexity is not associated with lower forecast errors. The findings highlight the practical importance of regularization, model parsimony, and chronological evaluation in country-level macroeconomic forecasting.

 

Keywords: GDP growth forecasting, Machine learning, Deep learning, Macroeconomic forecasting, Global panel data, Out-of-sample evaluation, Model comparison.

 

DOI https://doi.org/10.55463/issn.1674-2974.53.9.1


Full Text:

PDF


References


STOCK J H, WATSON M W. Macroeconomic Forecasting Using Diffusion Indexes. Journal of Business & Economic Statistics, 2002, 20(2): 147–162. DOI: 10.1198/073500102317351921.

GIANNONE D, REICHLIN L, SMALL D. Nowcasting: The Real-Time Informational Content of Macroeconomic Data. Journal of Monetary Economics, 2008, 55(4): 665–676. DOI: 10.1016/j.jmoneco.2008.05.010.

BAI J, NG S. Determining the Number of Factors in Approximate Factor Models. Econometrica, 2002, 70(1): 191–221. DOI: 10.1111/1468-0262.00273.

DE MOL C, GIANNONE D, REICHLIN L. Forecasting Using a Large Number of Predictors: Is Bayesian Shrinkage a Valid Alternative to Principal Components? Journal of Econometrics, 2008, 146(2): 318–328. DOI: 10.1016/j.jeconom.2008.08.011.

BANBURA M, GIANNONE D, REICHLIN L. Large Bayesian Vector Autoregressions. Journal of Applied Econometrics, 2010, 25(1): 71–92. DOI: 10.1002/jae.1137.

CARRIERO A, CLARK T E, MARCELLINO M. Bayesian VARs: Specification Choices and Forecast Accuracy. Journal of Applied Econometrics, 2015, 30(1): 46–73. DOI: 10.1002/jae.2315.

KOOP G, KOROBILIS D. Forecasting Inflation Using Dynamic Model Averaging. International Economic Review, 2012, 53(3): 867–886. DOI: 10.1111/j.1468-2354.2012.00704.x.

SCHORFHEIDE F, SONG D. Real-Time Forecasting With a Mixed-Frequency VAR. Journal of Business & Economic Statistics, 2015, 33(3): 366–380. DOI: 10.1080/07350015.2014.954707.

DIEBOLD F X, MARIANO R S. Comparing Predictive Accuracy. Journal of Business & Economic Statistics, 1995, 13(3): 253–263. DOI: 10.1080/07350015.1995.10524599.

WEST K D. Asymptotic Inference About Predictive Ability. Econometrica, 1996, 64(5): 1067–1084. DOI: 10.2307/2171956.

VARIAN H R. Big Data: New Tricks for Econometrics. Journal of Economic Perspectives, 2014, 28(2): 3–28. DOI: 10.1257/jep.28.2.3.

EINAV L, LEVIN J. Economics in the Age of Big Data. Science, 2014, 346(6210): 1243089. DOI: 10.1126/science.1243089.

MULLAINATHAN S, SPIESS J. Machine Learning: An Applied Econometric Approach. Journal of Economic Perspectives, 2017, 31(2): 87–106. DOI: 10.1257/jep.31.2.87.

BELLONI A, CHERNOZHUKOV V, HANSEN C. High-Dimensional Methods and Inference on Structural and Treatment Effects. Journal of Economic Perspectives, 2014, 28(2): 29–50. DOI: 10.1257/jep.28.2.29.

ATHEY S, IMBENS G W. Machine Learning Methods That Economists Should Know About. Annual Review of Economics, 2019, 11: 685–725. DOI: 10.1146/annurev-economics-080217-053433.

HOERL A E, KENNARD R W. Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics, 1970, 12(1): 55–67. DOI: 10.1080/00401706.1970.10488634.

TIBSHIRANI R. Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society: Series B, 1996, 58(1): 267–288. DOI: 10.1111/j.2517-6161.1996.tb02080.x.

BREIMAN L. Random Forests. Machine Learning, 2001, 45: 5–32. DOI: 10.1023/A:1010933404324.

BIAU G, SCORNET E. A Random Forest Guided Tour. TEST, 2016, 25: 197–227. DOI: 10.1007/s11749-016-0481-7.

FRIEDMAN J H. Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics, 2001, 29(5): 1189–1232. DOI: 10.1214/aos/1013203451.

FREUND Y, SCHAPIRE R E. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, 1997, 55(1): 119–139. DOI: 10.1006/jcss.1997.1504.

ANG A, PIAZZESI M, WEI M. What Does the Yield Curve Tell Us About GDP Growth? Journal of Econometrics, 2006, 131(1–2): 359–403. DOI: 10.1016/j.jeconom.2005.01.032.

MARCELLINO M, STOCK J H, WATSON M W. A Comparison of Direct and Iterated Multistep AR Methods for Forecasting Macroeconomic Time Series. Journal of Econometrics, 2006, 135(1–2): 499–526. DOI: 10.1016/j.jeconom.2005.07.020.

HYNDMAN R J, KOEHLER A B. Another Look at Measures of Forecast Accuracy. International Journal of Forecasting, 2006, 22(4): 679–688. DOI: 10.1016/j.ijforecast.2006.03.001.

MAKRIDAKIS S, SPILIOTIS E, ASSIMAKOPOULOS V. The M4 Competition: 100,000 Time Series and 61 Forecasting Methods. International Journal of Forecasting, 2020, 36(1): 54–74. DOI: 10.1016/j.ijforecast.2019.04.014.

ZHANG G, PATUWO B E, HU M Y. Forecasting With Artificial Neural Networks: The State of the Art. International Journal of Forecasting, 1998, 14(1): 35–62. DOI: 10.1016/S0169-2070(97)00044-7.

HORNIK K. Approximation Capabilities of Multilayer Feedforward Networks. Neural Networks, 1991, 4(2): 251–257. DOI: 10.1016/0893-6080(91)90009-T.

LECUN Y, BENGIO Y, HINTON G. Deep Learning. Nature, 2015, 521: 436–444. DOI: 10.1038/nature14539.

HOCHREITER S, SCHMIDHUBER J. Long Short-Term Memory. Neural Computation, 1997, 9(8): 1735–1780. DOI: 10.1162/neco.1997.9.8.1735.

MEDEIROS M C, VASCONCELOS G F R, VEIGA Á, ZILBERMAN E. Forecasting Inflation in a Data-Rich Environment: The Benefits of Machine Learning Methods. Journal of Business & Economic Statistics, 2021, 39(1): 98–119. DOI: 10.1080/07350015.2019.1637745.

GOULET COULOMBE P, LEROUX M, STEVANOVIC D, SURPRENANT S. How Is Machine Learning Useful for Macroeconomic Forecasting? Journal of Applied Econometrics, 2022, 37(5): 920–964. DOI: 10.1002/jae.2910.

GIACOMINI R, WHITE H. Tests of Conditional Predictive Ability. Econometrica, 2006, 74(6): 1545–1578. DOI: 10.1111/j.1468-0262.2006.00718.x.

CLARK T E, WEST K D. Approximately Normal Tests for Equal Predictive Accuracy in Nested Models. Journal of Econometrics, 2007, 138(1): 291–311. DOI: 10.1016/j.jeconom.2006.05.023.

MCCRACKEN M W, NG S. FRED-MD: A Monthly Database for Macroeconomic Research. Journal of Business & Economic Statistics, 2016, 34(4): 574–589. DOI: 10.1080/07350015.2015.1086655.

PESARAN M H, SCHUERMANN T, WEINER S M. Modeling Regional Interdependencies Using a Global Error-Correcting Macroeconometric Model. Journal of Business & Economic Statistics, 2004, 22(2): 129–162. DOI: 10.1198/073500104000000019.


Refbacks

  • There are currently no refbacks.