ENHANCING ECONOMIC FORECASTING WITH BAYESIAN NEURAL NETWORKS: A FOCUS ON GDP PREDICTION AND UNCERTAINTY QUANTIFICATION IN NIGERIA
DOI:
https://doi.org/10.60787/tnamp.v22.547Keywords:
Bayesian Neural Networks, Economic Forecasting, Deep Learning, Uncertainty QuantificationAbstract
This study produces a Bayesian Neural Network (BNN) to forecast GDP growth while quantifying prediction uncertainty which is often overlooked in traditional neural networks. By integrating Bayesian inference with deep learning, the model generates prediction intervals rather than single-point estimates, offering a probabilistic perspective crucial for decision-making under uncertainty. The BNN was initially trained on simulated data to validate its architecture and subsequently tested on real-world quarterly GDP data (2010-2023), monthly inflation rates, and interbank interest rates sourced from the Central Bank of Nigeria. The model employs Guassiandistributed weights and biases, uses Rectified Linear Unit (ReLU) activation functions, and optimizes training through the Adam algorithm. Results demonstrates that the BNN achieves strong predictive performance, with its prediction interval providing actionable insights for scenarios where uncertainty quantification is paramount. This approach improves GDP forecasting accuracy and provides a robust framework for analyzing volatile economic metrics in emerging economies like Nigeria.
Downloads
References
J. Heaton, N. G. Polson, and J. H. Witte, “Deep Learning for Finance: Deep Portfolios,” Appl. Stoch. Models Bus. Ind., vol. 32, no. 3, pp. 220–234, 2016, doi: 10.1002/asmb.2200.
G. Box, “Box and Jenkins: Time Series Analysis, Forecasting and Control,” in A Very British Affair: Six Britons and the Development of Time Series Analysis During the 20th Century, London: Palgrave Macmillan UK, 2013, pp. 161–215. doi: 10.1057/9781137291264_6.
C. A. Sims, “Macroeconomics and Reality,” Econometrica, vol. 48, no. 1, pp. 1–48, 1980.
Y. Huang and E. S. Yan, “Economic Recession Forecasts Using Machine Learning Models Based on the Evidence from the COVID-19 Pandemic,” Mod. Econ., vol. 14, no. 7, pp. 899–922, 2023.
J. Prosky, X. Song, A. Tan, and M. Zhao, “Sentiment predictability for stocks,” ArXiv Prepr. ArXiv171205785, 2017.
J. H. Stock and M. W. Watson, “Vector autoregressions,” J. Econ. Perspect., vol. 15, no. 4, pp. 101–115, 2001.
M. Banbura, D. Giannone, and L. Reichlin, “Large Bayesian vector auto regressions,” J. Appl. Econom., vol. 25, no. 1, pp. 71–92,
J. Barunik and L. Hanus, “Learning probability distributions in macroeconomics and finance,” ArXiv Prepr. ArXiv220406848, 2022.
Y. Zheng, Z. Xu, and A. Xiao, “Deep learning in economics: a systematic and critical review,” Artif. Intell. Rev., vol. 56, no. 9, pp. 9497–9539, 2023.
H. Wang and D.-Y. Yeung, “A survey on bayesian deep learning,” ACM Comput. Surv. CSUR, vol. 53, no. 5, pp. 1–37, 2020.
J. Geweke and C. Whiteman, “Bayesian forecasting,” Elsevier, Amsterdam, The Netherlands, Tech. Rep., 2006.
A. Brusaferri, M. Matteucci, P. Portolani, and A. Vitali, “Bayesian deep learning based method for probabilistic forecast of day-ahead electricity prices,” Appl. Energy, vol. 250, pp. 1158–1175, 2019.
S. Haykin, Neural networks: a comprehensive foundation. Prentice hall PTR, 1994.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by backpropagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, 1986.
K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Netw., vol. 2, no. 5, pp. 359–366, 1989.
O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, “Financial time series forecasting with deep learning: A systematic literature review: 2005–2019,” Appl. Soft Comput., vol. 90, p. 106181, 2020.
P. Raj, A. Mehta, and B. Singh, “Stock Market Prediction Using Deep Learning Algorithm: An Overview,” in International Conference on Innovative Computing and Communications: Proceedings of ICICC 2022, Volume 2, Springer Nature, 2022, p. 327.
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, pp. 1929–1958, 2014.
M. D. Liman, S. I. Osanga, E. S. Alu, and others, “Regularization effects in deep learning architecture,” J. Niger. Soc. Phys. Sci., pp. 1911–1911, 2024.
G. Koop and D. Korobilis, “Model uncertainty in panel vector autoregressive models,” Eur. Econ. Rev., vol. 81, pp. 115–131, 2016.
M. F. Steel, “Bayesian model averaging and forecasting,” Bull. EU US Inflat. Macroecon. Anal., vol. 200, pp. 30–41, 2011.
O. R. Olaniran, S. F. Olaniran, and J. Popoola, “Bayesian regularized neural network for forecasting naira-USD exchange rate,” in International Conference on Soft Computing and Data Mining, Springer, 2022, pp. 213–222.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Transactions of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
