Hybrid Bayesian ARIAM-ANN for Population Forecasting

Al-Qazaz, Ali

doi:10.25673/123548

Proceedings of International Conference on Applied Innovation in IT · 2026/03/31 · Vol. 14 · Issue 1 · pp. 141–152

Hybrid Bayesian ARIAM-ANN for Population Forecasting

Ali Mohammed Ali Chichan and Qutaiba Nabeel Nayef Al-Qazaz

📄 Download PDF DOI: 10.25673/123548

Abstract

This paper compares two forecasting methodologies: The Bayesian ARIMA model and a hybrid Bayesian ARIMA- ANN framework. This study uses historical population data for Iraq (1970–2024) to build predictive models for the period 2025–2034. In the hybrid model, the Bayesian method is employed to optimally estimate the ARIMA parameters while calculating forecast uncertainty intervals. The outputs of the Bayesian model are subsequently utilized as inputs for an artificial neural network (ANN). This integration allows the neural network to capture nonlinear patterns and complex relationships between the Bayesian outputs and actual population trends. The results, as indicated by the Mean Absolute Percentage Error (MAPE) criterion, demonstrated a substantial superiority of the hybrid model, which achieved the lowest criterion value of 0.31, in contrast to the Bayesian ARIMA model's value of 49.31. This improvement is attributed to the model's ability to combine the precision of Bayesian estimation with the flexibility of neural networks in modelling complex relationships. The study confirms that integrating Bayesian methods with artificial intelligence techniques significantly enhances the accuracy of long-term population forecasts, offering a reliable tool for strategic development planning.

Keywords

Autoregressive Integrated Moving Average Bayesian Method Markov Chain Monte Carlo Algorithm Artificial Neural Network Feed-Forward Back Propagation Forecasting.

References

M. Zakria and F. Muhammad, “Forecasting the population of Pakistan using ARIMA models,” Pakistan Journal of Agricultural Sciences, vol. 46, no. 3, pp. 214-223, 2009.
E. Cadenas and W. Rivera, “Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA–ANN model,” Renewable Energy, vol. 35, no. 12, pp. 2732-2738, Dec. 2010, [Online]. Available: https://doi.org/10.1016/j.renene.2010.04.022.
P. C. Padhan, “Application of ARIMA model for forecasting agricultural productivity in India,” J. Agric. Soc. Sci., vol. 8, no. 2, pp. 50-56, 2012.
I. Khandelwal, R. Adhikari, and G. Verma, “Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition,” in Proc. Int. Conf. Intell. Comput., Commun. Convergence, vol. 48, pp. 173-179, 2015, [Online]. Available: https://doi.org/10.1016/j.procs.2015.04.167.
J. Dai and S. Chen, “The application of ARIMA model in forecasting population data,” in Proc. 2nd Int. Conf. Phys., Math., Stat., vol. 1324, Art. no. 012100, 2019, [Online]. Available: https://doi.org/10.1088/1742-6596/1324/1/012100.
Z. Amry, “Bayesian estimate of parameters for ARMA model forecasting,” Tatra Mt. Math. Publ., vol. 75, pp. 23-32, 2020, [Online]. Available: https://doi.org/10.2478/tmmp-2020-0002.
M. N. Thorakkattle, S. Farhin, and A. A. Khan, “Forecasting the trends of Covid-19 and causal impact of vaccines using Bayesian structural time series and ARIMA,” Ann. Data Sci., vol. 9, no. 5, pp. 1025-1047, 2022, [Online]. Available: https://doi.org/10.1007/s40745-022-00418-4.
K. Z. Hossain, “Predicting the Demographic Future of Bangladesh: Application and Comparison of ARIMA and Combined Population Forecasts,” Romanian Statistical Review, vol. 2, 2024.
H. Song, S. F. Witt, and T. C. Jensen, “Tourism forecasting: Accuracy of alternative econometric models,” Int. J. Forecast., vol. 19, no. 1, pp. 123-141, 2003.
D. Asteriou and S. G. Hall, Applied Econometrics: A Modern Approach Using EViews and Microfit, Rev. ed. New York, NY, USA: Palgrave Macmillan, 2007.
G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ: John Wiley & Sons, 2016.
D. Barber, A. T. Cemgil, and S. Chiappa, Eds., Bayesian Time Series Models. Cambridge, U.K.: Cambridge University Press, 2011.
D. Gamerman and H. F. Lopes, Markov Chain Monte Carlo: Stochastic Simulation for Bayesian Inference, 2nd ed. Boca Raton, FL, USA: Chapman and Hall/CRC, 2006.
G. Lozano Orozco, “Markov Chain Monte Carlo approach to the analysis and forecast of grain prices and volatility monitoring,” M.S. thesis, Dept. Math. and Phys., Inst. Tecnol. y de Estudios Superiores de Occidente, Tlaquepaque, Mexico, 2022.
G. Casella and E. I. George, “Explaining the Gibbs Sampler,” The American Statistician, vol. 46, no. 3, pp. 167-174, Aug. 1992.
S. Chib and E. Greenberg, “Understanding the Metropolis-Hastings Algorithm,” The American Statistician, vol. 49, no. 4, pp. 327-335, Nov. 1995.
C. Fulton, “Bayesian Estimation and Forecasting of Time Series in statsmodels,” in Proc. 21st Python Sci. Conf. (SciPy 2022), pp. 89-96, 2022.
P. J. Green and D. I. Hastie, “Reversible Jump MCMC,” Genetics, vol. 155, no. 3, pp. 1391-1403, Jul. 2009.
D. H. A. Montcho, “Bayesian variable selection using data driven reversible jump: an application to schizophrenia data,” M.S. thesis, Interinstitutional Graduate Program in Statistics, Univ. of São Paulo, São Carlos, Brazil, 2022.
W. G. U. Turbey, “Identification of ARMA Models by Bayesian Methods Applied to Streamflow Data,” in 9th International Conference on Probabilistic Methods Applied to Power Systems, Stockholm, Sweden, Jun. 11-15, 2006.
K. Palit and D. Popovic, Computational Intelligence in Time Series Forecasting: Theory and Engineering Applications. London: Springer London, 2005.
K. Khairudin et al., “Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models,” Results in Engineering, vol. 22, p. 102072, Apr. 2024, [Online]. Available: https://doi.org/10.1016/j.rineng.2024.102072.
J. L. Ticknor, “A Bayesian regularized artificial neural network for stock market forecasting,” Expert Systems with Applications, vol. 40, no. 14, pp. 5501-5506, 2013.
H. Yonaba, F. Anctil, and V. Fortin, “Comparing sigmoid transfer functions for neural network multistep ahead streamflow forecasting,” Journal of Hydrologic Engineering, vol. 15, no. 4, pp. 275-283, Apr. 2010.
F. Farida, Y. Yuniar, M. F. Mayandah, and N. U. Nurissaidah, and D. Yuliati, “Forecasting population of Madiun Regency using ARIMA method,” CAUCHY: Jurnal Matematika Murni dan Aplikasi, vol. 7, no. 3, pp. 420-431, 2022.