A Hybrid Statistical and Probabilistic Model for Forecasting Uncertain Events
Article Sidebar
Main Article Content
Abstract
Forecasting uncertain events requires models that provide more than a single expected value, particularly when the target is a variable event count affected by seasonality, environmental conditions, and irregular outbreak peaks. This study proposes and evaluates a hybrid statistical-probabilistic framework for forecasting uncertain events, using weekly dengue incidence as an empirical case study. The framework integrates time-series structuring, lagged statistical features, environmental regression predictors, ensemble point forecasting, negative-binomial distribution fitting, and uncertainty interval estimation. A public dengue forecasting dataset containing 1,456 city-week observations from San Juan and Iquitos was used for chronological model evaluation. The proposed model was compared with seasonal naive, moving-average, log-ridge regression, random-forest, and gradient-boosting baselines using mean absolute error (MAE), root mean squared error (RMSE), symmetric mean absolute percentage error, prediction-interval coverage, and interval width. The hybrid model achieved the lowest validation error, with an MAE of 5.908 and an RMSE of 9.874, outperforming the seasonal naive baseline by a large margin and modestly improving over the individual ensemble learners. The probabilistic layer produced empirically conservative uncertainty intervals, with 87.67% coverage for the nominal 80% interval and 93.84% coverage for the nominal 90% interval. Feature-importance results showed that recent case history was the strongest predictor, while precipitation, temperature, humidity, and time-index variables contributed additional contextual information. The study contributes an interpretable forecasting framework that connects statistical temporal structure with probabilistic event-risk estimation. The main limitation is that the empirical evidence is based on two locations, so future research should test the framework across broader domains of outbreak, climate, financial, and operational events.
Downloads
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
1. Al Mobin, M., et al. (2024). Forecasting dengue in Bangladesh using meteorological parameters and machine learning models. Scientific Reports, 14, Article 31136. doi: 10.1038/s41598-024-83770-0 DOI: https://doi.org/10.1038/s41598-024-83770-0
2. Baharom, M., Ahmad, N., & Hod, R. (2022). Dengue early warning system as outbreak prediction tool: A systematic review. Risk Management and Healthcare Policy, 15, 871-886. doi: 10.2147/RMHP.S361106 DOI: https://doi.org/10.2147/RMHP.S361106
3. Barboza, L. A., et al. (2022). Assessing dengue fever risk in Costa Rica by using climate variables and machine learning techniques. arXiv. doi: 10.48550/arXiv.2204.01483 DOI: https://doi.org/10.1371/journal.pntd.0011047
4. Ben Taieb, S., & Hyndman, R. J. (2014). A gradient boosting approach to the Kaggle load forecasting competition. International Journal of Forecasting, 30(2), 382-394. doi: 10.1016/j.ijforecast.2013.07.005 DOI: https://doi.org/10.1016/j.ijforecast.2013.07.005
5. Benedum, C. M., et al. (2020). Weekly dengue forecasts in Iquitos, Peru; San Juan, Puerto Rico; and Singapore. PLOS Neglected Tropical Diseases, 14(10), Article e0008710. doi: 10.1371/journal.pntd.0008710 DOI: https://doi.org/10.1371/journal.pntd.0008710
6. Buczak, A. L., et al. (2014). Prediction of high incidence of dengue in the Philippines. PLOS Neglected Tropical Diseases, 8(4), Article e2771. doi: 10.1371/journal.pntd.0002771 DOI: https://doi.org/10.1371/journal.pntd.0002771
7. Chen, Y., et al. (2018). Neighbourhood level real-time forecasting of dengue cases in tropical urban Singapore. BMC Medicine, 16, Article 129. doi: 10.1186/s12916-018-1103-6 DOI: https://doi.org/10.1186/s12916-018-1108-5
8. Chuang, T.-W., Chaves, L. F., & Chen, P.-J. (2017). Effects of local and regional climatic fluctuations on dengue outbreaks in southern Taiwan. PLOS ONE, 12(6), Article e0178698. doi: 10.1371/journal.pone.0178698 DOI: https://doi.org/10.1371/journal.pone.0178698
9. da Silva, S. T., et al. (2024). When climate variables improve dengue forecasting: A machine learning approach. European Physical Journal Special Topics. doi: 10.1140/epjs/s11734-024-01201-7 DOI: https://doi.org/10.1140/epjs/s11734-024-01201-7
10. Gneiting, T., & Raftery, A. E. (2007). Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102(477), 359-378. doi: 10.1198/016214506000001437 DOI: https://doi.org/10.1198/016214506000001437
11. Gneiting, T., Balabdaoui, F., & Raftery, A. E. (2007). Probabilistic forecasts, calibration and sharpness. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 69(2), 243-268. doi: 10.1111/j.1467-9868.2007.00587.x DOI: https://doi.org/10.1111/j.1467-9868.2007.00587.x
12. Hyndman, R. J., & Khandakar, Y. (2008). Automatic time series forecasting: The forecast package for R. Journal of Statistical Software, 27(3), 1-22. doi: 10.18637/jss.v027.i03 DOI: https://doi.org/10.18637/jss.v027.i03
13. Johansson, M. A., Reich, N. G., Hota, A., Brownstein, J. S., & Santillana, M. (2016). Evaluating the performance of infectious disease forecasts: A comparison of climate-driven and seasonal dengue forecasts for Mexico. Scientific Reports, 6, Article 33707. doi: 10.1038/srep33707 DOI: https://doi.org/10.1038/srep33707
14. Khosravi, A., Nahavandi, S., Creighton, D., & Atiya, A. F. (2011). Lower upper bound estimation method for construction of neural network-based prediction intervals. IEEE Transactions on Neural Networks, 22(3), 337-346. doi: 10.1109/TNN.2010.2096824 DOI: https://doi.org/10.1109/TNN.2010.2096824
15. Leung, X. Y., et al. (2023). A systematic review of dengue outbreak prediction models: Current scenario and future directions. PLOS Neglected Tropical Diseases, 17(2), Article e0010631. doi: 10.1371/journal.pntd.0010631 DOI: https://doi.org/10.1371/journal.pntd.0010631
16. Lippi, C. A., et al. (2019). Investigating the utility of satellite-based rainfall estimates for dengue early warning in Mexico. PLOS Neglected Tropical Diseases, 13(11), Article e0007564. doi: 10.1371/journal.pntd.0007564 DOI: https://doi.org/10.1371/journal.pntd.0007564
17. Lowe, R., et al. (2018). Nonlinear and delayed impacts of climate on dengue risk in Barbados: A modelling study. PLOS Medicine, 15(7), Article e1002613. doi: 10.1371/journal.pmed.1002613 DOI: https://doi.org/10.1371/journal.pmed.1002613
18. Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2020). The M4 Competition: 100,000 time series and 61 forecasting methods. International Journal of Forecasting, 36(1), 54-74. doi: 10.1016/j.ijforecast.2019.04.014 DOI: https://doi.org/10.1016/j.ijforecast.2019.04.014
19. Marques-Toledo, C. de A., et al. (2017). Dengue prediction via the web: Tweets are a useful tool for estimating and forecasting dengue at the country and city levels. PLOS Neglected Tropical Diseases, 11(7), Article e0005729. doi: 10.1371/journal.pntd.0005729 DOI: https://doi.org/10.1371/journal.pntd.0005729
20. Petropoulos, F., et al. (2022). Forecasting: Theory and practice. International Journal of Forecasting, 38(3), 705-871. doi: 10.1016/j.ijforecast.2021.11.001 DOI: https://doi.org/10.1016/j.ijforecast.2021.11.001
21. Racloz, V., Ramsey, R., Tong, S., & Hu, W. (2012). Surveillance of dengue fever virus: A review of epidemiological models and early warning systems. PLOS Neglected Tropical Diseases, 6(5), Article e1648. doi: 10.1371/journal.pntd.0001648 DOI: https://doi.org/10.1371/journal.pntd.0001648
22. Ramosaj, B., Schultheis, J. S., & Pauly, M. (2021). Constructing valid prediction intervals with random forests. arXiv. doi: 10.48550/arXiv.2103.05766
23. Roster, K., Connaughton, C., & Rodrigues, F. A. (2022). Machine-learning-based forecasting of dengue fever in Brazilian cities using epidemiologic and meteorological variables. American Journal of Epidemiology, 191(10), 1803-1812. doi: 10.1093 /aje/kwac090 DOI: https://doi.org/10.1093/aje/kwac090
24. Salinas, D., Flunkert, V., Gasthaus, J., & Januschowski, T. (2020). DeepAR: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3), 1181-1191. doi: 10.1016/j.ijforecast.2019.07.001 DOI: https://doi.org/10.1016/j.ijforecast.2019.07.001
25. Sylvestre, E., et al. (2022). Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review. PLOS Neglected Tropical Diseases, 16(1), Article e0010056. doi: 10.1371/journal.pntd.0010056 DOI: https://doi.org/10.1371/journal.pntd.0010056
26. Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37-45. doi: 10.1080/00031305.2017.1380080 DOI: https://doi.org/10.1080/00031305.2017.1380080
27. Tian, Q., Nordman, D. J., & Meeker, W. Q. (2022). Methods to compute prediction intervals: A review and new results. Statistical Science, 37(4), 580-597. doi: 10.1214/21-STS842 DOI: https://doi.org/10.1214/21-STS842
28. Wikle, C. K., Zammit-Mangion, A., & Cressie, N. (2019). Spatio-temporal statistics with R. CRC Press. DOI: https://doi.org/10.1201/9781351769723
29. Xu, H., Mei, S., Bates, S., Taylor, J., & Tibshirani, R. (2023). Uncertainty intervals for prediction errors in time series forecasting. arXiv. doi: 10.48550/arXiv.2309.07435
30. Yoon, T., Park, Y., Ryu, E. K., & Wang, Y. (2022). Robust probabilistic time series forecasting. arXiv. doi: 10.48550/arXiv.2202.11910
31. DrivenData. (2016). DengAI: Predicting disease spread [Data set]. DrivenData.