Hybrid TBATS-Extreme Learning Machine Model for Forecasting the Number of Train Passengers  in Java Excluding Jabodetabek

Salsa Agung Oktariana; Achmad Efendi; Rahma Fitriani

doi:10.31764/jtam.v10i4.39382

Hybrid TBATS-Extreme Learning Machine Model for Forecasting the Number of Train Passengers in Java Excluding Jabodetabek

Salsa Agung Oktariana, Achmad Efendi, Rahma Fitriani

Abstract

Railway transportation is one of the most important modes of transport in Java, yet the COVID-19 pandemic caused major disruptions to passenger patterns that made the forecasting process considerably more challenging. Previous research has compared TBATS and Extreme Learning Machine (ELM) models separately, but no one has tried to combine the two in one hybrid model. This research fills this gap by building a hybrid TBATS-ELM model using Non-Negative Least Squares (NNLS) to determine the best combination weights between the two models. The data used consists of monthly railway passenger data in Java excluding Jabodetabek from January 2006 to December 2025, comprising 240 observations divided into training, validation, and testing sets. The combination weights were estimated on the validation data using NNLS to produce an optimal and interpretable combination. Test results show that the hybrid model reduced forecast error by 74.27% compared to the standalone TBATS model, with a final MAPE of 11.47% classified as accurate. These findings suggest that combining a seasonal statistical model with a machine learning approach can offer a more reliable solution when data experiences extreme structural disruptions such as those caused by the pandemic.

Keywords

TBATS; Extreme Learning Machine; Hybrid Model; Non-Negative Least Square.

Full Text:

DOWNLOAD [PDF]

References

Badan Pusat Statistik. (2025). Statistik Transportasi Darat 2024.

Cerqueira, V., Torgo, L., & Mozetič, I. (2020). Evaluating time series forecasting models: an empirical study on performance estimation methods. Machine Learning, 109(11), 1997–2028. https://doi.org/10.1007/s10994-020-05910-7

Chan, F., & Pauwels, L. L. (2018). Some Theoretical Results on Forecast Combinations. International Journal of Forecasting, 34(1), 64–74. https://doi.org/https://doi.org/10.1016/j.ijforecast.2017.08.005

Chen, P., Vivian, A., & Ye, C. (2022). Forecasting carbon futures price: a hybrid method incorporating fuzzy entropy and extreme learning machine. Annals of Operations Research, 313(1), 559–601. https://doi.org/10.1007/s10479-021-04406-4

Claeskens, G., Magnus, J. R., Vasnev, A. L., & Wang, W. (2016). The forecast combination puzzle: A simple theoretical explanation. International Journal of Forecasting, 32(3), 754–762. https://doi.org/https://doi.org/10.1016/j.ijforecast.2015.12.005

Clements, M. P. (2017). Sir Clive W.J. Granger’s Contributions to Forecasting. European Journal of Pure and Applied Mathematics, 10(1), 30–57. https://doi.org/https://www.ejpam.com/ejpam/article/view/2949

de Mattos Neto, P. S. G., de Oliveira, J. F. L., Bassetto, P., Siqueira, H. V., Barbosa, L., Alves, E. P., Marinho, M. H. N., Rissi, G. F., & Li, F. (2021). Energy consumption forecasting for smart meters using extreme learning machine ensemble. Sensors, 21(23), 1–18. https://doi.org/10.3390/s21238096

Diebold, F. X., & Shin, M. (2019). Machine learning for regularized survey forecast combination: Partially-egalitarian LASSO and its derivatives. International Journal of Forecasting, 35(4), 1679–1691. https://doi.org/https://doi.org/10.1016/j.ijforecast.2018.09.006

Hightower, A., Ziedan, A., Guo, J., Zhu, X., & Brakewood, C. (2024). A comparison of time series methods for post-COVID transit ridership forecasting. Journal of Public Transportation, 26, 1–15. https://doi.org/10.1016/j.jpubtr.2024.100097

Houssein, E. H., Mohamed, M., Younis, E. M. G., & Mohamed, W. M. (2025). Artificial intelligence and classical statistical models for time series forecasting: a comprehensive review. Journal of Big Data, 12(1), 1–38. https://doi.org/10.1186/s40537-025-01318-z

Huang, G. Bin, Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1–3), 489–501. https://doi.org/10.1016/j.neucom.2005.12.126

Kourentzes, N., Barrow, D., & Petropoulos, F. (2019). Another look at forecast selection and combination: Evidence from forecast pooling. International Journal of Production Economics, 209, 226–235. https://doi.org/10.1016/j.ijpe.2018.05.019

Lawson, C. L., & Hanson, R. J. (1995). Solving Least Squares Problems (Vol. 15). Society for Industrial and Applied Mathematics (SIAM). https://doi.org/10.1137/1.9781611971217

Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 379(2194), 20200209. https://doi.org/10.1098/rsta.2020.0209

Livera, A. M., Hyndman, R. J., & Snyder, R. D. (2011). Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing. Journal of the American Statistical Association, 106(496), 1513–1527. https://doi.org/10.1198/jasa.2011.tm09771

Mahsup, Febriani, P. A., Syaharuddin, Mandailina, V., Abdillah, & Ibrahim. (2024). Accuracy Rate of Least Square Support Vector Machine Method and Its Various Modifications: A Forecasting Evaluation on Multi-Type Data. Ingenierie Des Systemes d’Information, 29(3), 1209–1218. https://doi.org/10.18280/isi.290337

Munim, Z. H. (2022). State-space TBATS model for container freight rate forecasting with improved accuracy. Maritime Transport Research, 3, 1–14. https://doi.org/10.1016/j.martra.2022.100057

Nar, M., & Arslankaya, S. (2022). Passenger demand forecasting for railway systems. Open Chemistry, 20(1), 105–119. https://doi.org/10.1515/chem-2022-0124

Perone, G. (2022). Comparison of ARIMA, ETS, NNAR, TBATS and Hybrid Models to Forecast the Second Wave of COVID-19 Hospitalizations in Italy. European Journal of Health Economics, 23(6), 917–940. https://doi.org/10.1007/s10198-021-01347-4

Roccazzella, F., Gambetti, P., & Vrins, F. (2022). Optimal and robust combination of forecasts via constrained optimization and shrinkage. International Journal of Forecasting, 38(1), 97–116. https://doi.org/10.1016/j.ijforecast.2021.04.002

Sattar, A. M. A., Ertuğrul, Ö. F., Gharabaghi, B., McBean, E. A., & Cao, J. (2019). Extreme learning machine model for water network management. Neural Computing and Applications, 31(1), 157–169. https://doi.org/10.1007/s00521-017-2987-7

Segura-Heras, J. V., Bermúdez, J. D., Corberán-Vallet, A., & Vercher, E. (2022). Analysis of Weighting Strategies for Improving the Accuracy of Combined Forecasts. Mathematics, 10(5), 1–12. https://doi.org/10.3390/math10050725

Svetunkov, I., & Boylan, J. E. (2020). State-space ARIMA for supply-chain forecasting. International Journal of Production Research, 58(3), 818–827. https://doi.org/10.1080/00207543.2019.1600764

Zhao, D., & Zhang, H. (2022). The research on TBATS and ELM models for prediction of human brucellosis cases in mainland China: a time series study. BMC Infectious Diseases, 22(1), 1–12. https://doi.org/10.1186/s12879-022-07919-w

Zhao, S., & Mi, X. (2019). A Novel Hybrid Model for Short-Term High-Speed Railway Passenger Demand Forecasting. IEEE Access, 7, 175681–175692. https://doi.org/10.1109/ACCESS.2019.2957612

Zhu, K., Xun, P., Li, W., Li, Z., & Zhou, R. (2019). Prediction of Passenger Flow in Urban Rail Transit Based on Big Data Analysis and Deep Learning. IEEE Access, 7, 142272–142279. https://doi.org/10.1109/ACCESS.2019.2944744

DOI: https://doi.org/10.31764/jtam.v10i4.39382