Prophet with Google Trends for Forecasting Train Passengers in Java

Kiki Ferawati; Winita Sulandari; Nur Arina Bazilah Kamisan

doi:10.52436/1.jutif.2026.7.2.5306

Authors

Kiki Ferawati Department of Statistics, Universitas Sebelas Maret, Indonesia
Winita Sulandari Department of Statistics, Universitas Sebelas Maret, Indonesia
Nur Arina Bazilah Kamisan Department of Mathematical Sciences, Universiti Teknologi Malaysia, Malaysia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5306

Keywords:

External Regressor, Forecast, Google Trends, Prophet, Train Passengers

Abstract

As a popular transportation method for long-distance travel, trains were also a preferred choice during the homecoming period before Eid Al-Fitr, one of the major religious holidays in Indonesia. During this period, known locally as ‘mudik,’ millions of people travel from the urban cities back to their hometowns to celebrate with their families, creating a significant surge in transportation demand. However, since the holiday follows the Islamic calendar, which changes slightly every year, forecasting train passengers becomes tricky, thus requiring a different approach to achieve accurate predictions. This study utilizes the Prophet method to forecast train passengers in Java (excluding the Jabodetabek area) using the data from 2006 to 2024. We also incorporated the COVID-19 period as a fixed external regressor, along with external regressors from Google Trends data using the keywords ‘kereta api’, ‘mudik’, and ‘lebaran’, which are commonly searched by the public in relation to train travel and the Eid homecoming period. The results on the test set, 2024 data, showed that the word ‘mudik’ was the most effective in improving forecast accuracy, with a MAPE of 9.12 and RMSE of 797.76, a decrease of 11.57% and 9.34% compared to the updated baseline. This indicates that public search behavior around the term ‘mudik’ closely aligns with actual travel demand patterns. The findings of this study suggest that Prophet with external regressors are capable of forecasting train passengers and Google Trends can be a valuable addition for capturing data patterns related to specific phenomenon.

Downloads

Download data is not yet available.

References

M. F. Yusuf, A. Samingan, and M. C. Huda, “Sociocultural meaning of Mudik on NU online website,” Islamic Quarterly, vol. 64, no. 4, pp. 485 – 506, 2020.

A. F. Saputri, A. Hoyyi, and S. Sugito, “Prediksi Jumlah Penumpang Kereta Api Menggunakan Model Variasi Kalender dengan Deteksi Outlier (Studi Kasus : PT. Kereta Api Indonesia DAOP IV Semarang),” Jurnal Gaussian, vol. 6, no. 3, pp. 281–289, Jan. 2018, doi: 10.14710/J.GAUSS.6.3.281-289.

M. S. Akbar, D. A. Safira, R. Fadhilah, S. Damayanti, Riskianto, and K. Puthy, “Eid Al-Fitr Influences The Number of Train Passengers on The Sumatra Island (Calendar Variations Time Series Model),” Barekeng, vol. 18, no. 4, pp. 2191–2202, Oct. 2024, doi: 10.30598/BAREKENGVOL18ISS4PP2191-2202.

N. Fitriyati, M. Y. Wijaya, M. I. F. Pagri, and N. Inayah, “Forecasting domestic ship passengers in the Makassar Port using feed-forward neural network and SARIMAX,” AIP Conf. Proc., vol. 2641, Dec. 2022, doi: 10.1063/5.0115296.

M. Silfiani and F. N. Hayati, “Forecasting Number of Train Passengers Using Time Series Regression Integrated Calendar Variation and COVID 19 Intervention,” Jurnal Matematika Sains dan Teknologi, no. May 2024, 2024, doi: 10.33830/jmst.v25i1.4941.2024.

B. Kumar Jha and S. Pande, “Time Series Forecasting Model for Supermarket Sales using FB-Prophet,” Proceedings - 5th International Conference on Computing Methodologies and Communication, ICCMC 2021, pp. 547–554, Apr. 2021, doi: 10.1109/ICCMC51019.2021.9418033.

C. B. Aditya Satrio, W. Darmawan, B. U. Nadia, and N. Hanafiah, “Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET,” Procedia Comput. Sci., vol. 179, pp. 524–532, Jan. 2021, doi: 10.1016/J.PROCS.2021.01.036.

T. Toharudin, R. S. Pontoh, R. E. Caraka, S. Zahroh, Y. Lee, and R. C. Chen, “Employing long short-term memory and Facebook prophet model in air temperature forecasting,” Commun. Stat. Simul. Comput., vol. 52, no. 2, pp. 279–290, 2023, doi: 10.1080/03610918.2020.1854302.

K. K. R. Samal, K. S. Babu, S. K. Das, and A. Acharaya, “Time series based air pollution forecasting using SARIMA and prophet model,” ACM International Conference Proceeding Series, pp. 80–85, Aug. 2019, doi: 10.1145/3355402.3355417.

H. Abbasimehr, M. Shabani, and M. Yousefi, “A comparative assessment of SARIMA, LSTM RNN and Fb Prophet models to forecast total and peak monthly energy demand for India,” Energy Policy, vol. 168, p. 113097, Sep. 2022, doi: 10.1016/j.cie.2020.106435.

J. Pragalathan and D. Schramm, “Comparison of SARIMA, Fb-Prophet and Neural Prophet Models for Traffic Flow Predictions at a Busy Urban Intersection,” Lecture Notes in Civil Engineering, vol. 529 LNCE, pp. 127–143, 2024, doi: 10.1007/978-981-97-4852-5_10.

X. Zhao, H. Guan, H. Sun, and J. Lu, “A Prophet-Based Passenger Flow Prediction Model on IC Card Data,” Lecture Notes in Electrical Engineering, vol. 901 LNEE, pp. 1082–1092, 2022, doi: 10.1007/978-981-19-2259-6_95.

S. Xiong and J. Li, “Study on subway passenger flow forecast based on time series analysis method,” in Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), SPIE, Dec. 2021, pp. 1474–1478. doi: 10.1117/12.2619729.

A. Meza, A. Acuna, and J. Santisteban, “Predicting Public Transport Passenger Using Machine Learning Algorithms,” 10th International Conference on Digital Arts, Media and Technology, DAMT 2025 and 8th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2025, pp. 47–52, 2025, doi: 10.1109/ECTIDAMTNCON64748.2025.10962052.

R. S. Pontoh, S. Zahroh, H. R. Nurahman, R. I. Aprillion, A. Ramdani, and D. I. Akmal, “Applied of feed-forward neural network and facebook prophet model for train passengers forecasting,” J. Phys. Conf. Ser., vol. 1776, no. 1, p. 012057, Feb. 2021, doi: 10.1088/1742-6596/1776/1/012057.

B. A. Hakim, Billy, K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, “Time Series Model for Train Passenger Forecasting,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 19, no. 2, pp. 755–766, Apr. 2025, doi: 10.30598/BAREKENGVOL19ISS2PP755-766.

A. Brodeur, A. E. Clark, S. Fleche, and N. Powdthavee, “COVID-19, lockdowns and well-being: Evidence from Google Trends,” J. Public Econ., vol. 193, p. 104346, Jan. 2021, doi: 10.1016/J.JPUBECO.2020.104346.

A. I. Bento, T. Nguyen, C. Wing, F. Lozano-Rojas, Y. Y. Ahn, and K. Simon, “Evidence from internet search data shows information-seeking responses to news of local COVID-19 cases,” Proc. Natl. Acad. Sci. U. S. A., vol. 117, no. 21, pp. 11220–11222, May 2020, doi: 10.1073/PNAS.2005335117.

L. Bulut, “Google Trends and the forecasting performance of exchange rate models,” J. Forecast., vol. 37, no. 3, pp. 303–315, Apr. 2018, doi: 10.1002/FOR.2500.

K. Nikolopoulos, S. Punia, A. Schäfers, C. Tsinopoulos, and C. Vasilakis, “Forecasting and planning during a pandemic: COVID-19 growth rates, supply chain disruptions, and governmental decisions,” Eur. J. Oper. Res., vol. 290, no. 1, pp. 99–115, Apr. 2021, doi: 10.1016/J.EJOR.2020.08.001.

A. Mavragani, G. Ochoa, and K. P. Tsagarakis, “Assessing the methods, tools, and statistical approaches in Google trends research: Systematic review,” J. Med. Internet Res., vol. 20, no. 11, Nov. 2018, doi: 10.2196/JMIR.9366,.

H. Jie, H. Zou, and Q. Xu, “Forecasting Daily MRT Passenger Flow in Taipei Based on Google Search Queries,” Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021, pp. 46–50, 2021, doi: 10.1109/ISCSIC54682.2021.00020.

S. Lertyongphati, “Impact of External Factors on Air Passenger Demand Prediction Using Machine Learning,” ACM International Conference Proceeding Series, Dec. 2023, doi: 10.1145/3628454.3628462.

S. K. Prilistya, A. E. Permanasari, and S. Fauziati, “The Effect of the COVID-19 Pandemic and Google Trends on the Forecasting of International Tourist Arrivals in Indonesia,” TENSYMP 2021 - 2021 IEEE Region 10 Symposium, Aug. 2021, doi: 10.1109/TENSYMP52854.2021.9550838.

P. D. W. Oktama, “Nowcasting Jumlah Penumpang Kereta Api di Indonesia Menggunakan Indeks Google Trends,” Seminar Nasional Official Statistics, vol. 2021, no. 1, pp. 958–967, Nov. 2021, doi: 10.34123/semnasoffstat.v2021i1.820.

S. J. Taylor and B. Letham, “Forecasting at Scale,” American Statistician, vol. 72, no. 1, pp. 37–45, Jan. 2018, doi: 10.1080/00031305.2017.1380080.

Y. Ensafi, S. H. Amin, G. Zhang, and B. Shah, “Time-series forecasting of seasonal items sales using machine learning – A comparative analysis,” International Journal of Information Management Data Insights, vol. 2, no. 1, p. 100058, Apr. 2022, doi: 10.1016/J.JJIMEI.2022.100058.

S. Setiati and M. K. Azwar, “COVID-19 and Indonesia,” Acta Med. Indones., vol. 52, no. 1, pp. 84 – 89, 2020.

M. Hu et al., “Risk of Coronavirus Disease 2019 Transmission in Train Passengers: An Epidemiological and Modeling Study,” Clinical Infectious Diseases, vol. 72, no. 4, pp. 604–610, Feb. 2021, doi: 10.1093/CID/CIAA1057.

Widyawan, M. Syarif, and A. R. Pratama, “Mobility of Indonesian during Early Pandemic: Insights from Mobile Positioning Data,” ICITEE 2022 - Proceedings of the 14th International Conference on Information Technology and Electrical Engineering, pp. 136–141, 2022, doi: 10.1109/ICITEE56407.2022.9954078.

A. L. Tantri and S. Waluyo, “Polemic of Mudik in Indonesia: How People Deal with Government Regulation Related to Covid-19,” E3S Web of Conferences, vol. 317, Nov. 2021, doi: 10.1051/E3SCONF/202131704004.

S. D. Rismawati and I. Abdullah, “Beyond health regulations: Lessons from vaccine acceptance and the prevention of the COVID-19 pandemic,” Cogent Soc. Sci., vol. 9, no. 2, 2023, doi: 10.1080/23311886.2023.2258671.

A. Aswadi, M. Hadijati, and I. G. A. W. Wardhana, “Calendar variation model for ticket sales forecasting at Kayangan Port, East Lombok,” AIP Conf. Proc., vol. 2641, Dec. 2022, doi: 10.1063/5.0115066.