A Hybrid Forecasting Framework for Iraq's Life Expectancy Prediction: Integrating Prophet's Time Series Decomposition with XGBoost's Machine Learning Capabilities for Improved Accuracy
Article Sidebar
THIS IS AN OPEN ACCESS ARTICLE UNDER THE CC BY LICENSE
Main Article Content
Abstract
Time series forecasting is a critical task in various fields such as economics, healthcare, and supply chain management, where accurate predictions are essential for informed decision-making. This study focuses on forecasting life expectancy in Iraq, a complex task influenced by socio-economic, healthcare, and demographic factors. Traditional statistical methods often struggle to capture the non-linear relationships inherent in such data, prompting the exploration of advanced forecasting models. This research employs a hybrid approach, integrating Prophet, a time series decomposition tool developed by Facebook, with XGBoost, a powerful machine learning algorithm known for its ability to model non-linear relationships. Despite previous research has explored hybrid models, to the best of the researchers' knowledge, this is the first study to apply such a hybrid model to this specific dataset. The hybrid model aims to combine Prophet's strength in capturing trends and seasonality with XGBoost's capability to model complex interactions and residuals. The hybrid approach addresses the limitations of traditional models and machine learning techniques when used individually. This research fills a gap in the literature by applying this innovative framework to Iraq, providing policymakers with more accurate forecasts for healthcare and social service planning. Results indicate that the hybrid model provides more accurate and realistic predictions compared to the individual Prophet and XGBoost models. Although, this study shows hybrid models improve life expectancy predictions in Iraq. Future research should factor in healthcare, socio-political, and environmental influences. These models can guide better health policies in Iraq.
Downloads
Article Details
References
Ahmed, N. K., Atiya, A. F., Gayar, N. E., & El-Shishiny, H. (2010). An empirical comparison of machine learning models for time series forecasting. Econometric reviews, 29(5-6), 594-621.
Cleveland, R. B., Cleveland, W. S., McRae, J. E., & Terpenning, I. (1990). STL: A seasonal-trend decomposition. J. off. Stat, 6(1), 3-73.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). Statistical and Machine Learning forecasting methods: Concerns and ways forward. PloS one, 13(3), e0194889.
Shmueli, G., & Lichtendahl Jr, K. C. (2016). Time Series Forecasting With R.
Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37-45.
Wolpert, D. H. (1992). Stacked generalization. Neural networks, 5(2), 241-259.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
Ali, T. H., Mahmood, A. P. D. S. H., & Wahdi, A. P. D. A. S. (2022). Using Proposed Hybrid method for neural networks and wavelet to estimate time series model. Tikrit Journal of Administrative and Economic Sciences, 18(57 part 3).
Karim, A. J. M., & Ahmed, N. M. (2023). Multivariate time series analysis of COVID-19 Pandemic and gold price by using Error Corrections Model. Tikrit Journal of Administrative and Economic Sciences, 19(64 part 1).
Wang, J., Du, X., & Qi, X. (2022). Strain prediction for historical timber buildings with a hybrid Prophet-XGBoost model. Mechanical Systems and Signal Processing, 179, 109316.
Odhiambo, S. O., Nyakundi, C., & Waititu, H. (2024). Developing a Hybrid ARIMA-XGBOOST Model for Analysing Mobile Money Transaction Data in Kenya. Asian Journal of Probability and Statistics, 26(10), 10-9734.
Zeng, S., Liu, C., Zhang, H., Zhang, B., & Zhao, Y. (2025). Short-Term Load Forecasting in Power Systems Based on the Prophet–BO–XGBoost Model. Energies, 18(2), 227.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).