SavedAdd your journal

Journals / Endüstri Mühendisliği / 2023 / Cilt: 34 Sayı: 3

FORECASTING PUBLIC TRANSPORTATION PASSENGER DEMAND WITH SARIMA AND PROPHET METHODS

TOPLU TAŞIMA YOLCU TALEBİNİN SARIMA VE PROPHET YÖNTEMLERİ İLE TAHMİNİ

Gizem Küçüker(Manisa Celal Bayar Üniversitesi)0000-0002-4016-1541
Özlem Uzun Araz(MANİSA CELÂL BAYAR ÜNİVERSİTESİ)0000-0001-5630-6170
Pages
334–356
Publication Date
2023-12-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of the modeling, the MAPE values of SARIMA and Prophet methods were calculated as 0.11 and 0.13, respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In transport systems, knowing passenger demand is a vital task for many operational activities, such as determining routes, planning schedules, and frequency, and optimizing the number of employees.
📊
Key Findings & Data:This study aims to compare the performance of the SARIMA method, which is one of the most preferred Box-Jenkins methodologies in the literature, and the Prophet method developed by Facebook in 2017, in forecasting the number of passengers in public transportation vehicles and to evaluate the methods.
💡
Conclusion & Impact:As a result of the modeling, the MAPE values of SARIMA and Prophet methods were calculated as 0.11 and 0.13, respectively.
🔬Design:Modeling & Simulation
📍Scope:2017 Verileri
⚙️Variables:Talep tahmini · Box-Jenkins · Prophet

Abstract

In transport systems, knowing passenger demand is a vital task for many operational activities, such as determining routes, planning schedules, and frequency, and optimizing the number of employees. However, the demand's irregularity, trend, and seasonality components make it challenging to forecast. Recently, modern artificial intelligence techniques have been used in addition to traditional demand forecasting methods. This study aims to compare the performance of the SARIMA method, which is one of the most preferred Box-Jenkins methodologies in the literature, and the Prophet method developed by Facebook in 2017, in forecasting the number of passengers in public transportation vehicles and to evaluate the methods. Two successful forecasting models were developed using the two methods. As a result of the modeling, the MAPE values of SARIMA and Prophet methods were calculated as 0.11 and 0.13, respectively.

Özet

Taşıma sistemlerinde yolcu talebinin bilinmesi; rotaların belirlenmesi, sefer saatlerinin ve sıklığının planlanması, çalışan sayısının optimize edilmesi gibi birçok operasyon faaliyeti için hayati bir görevdir. Bununla birlikte talebin düzensizliği, trend ve mevsimsellik bileşenlerini barındırması, tahmin edilebilmesini zor bir hale sokmaktadır. Son zamanlarda geleneksel talep tahmin yöntemlerinin yanı sıra modern yapay zekâ teknikleri de kullanılmaya başlanmıştır. Bu çalışmada, literatürde sıklıkla tercih edilen Box-Jenkins metodolojisinden SARIMA yöntemi ile 2017’de Facebook tarafından geliştirilen Prophet yönteminin toplu taşıma araçlarındaki yolcu sayısı tahminindeki performanslarının karşılaştırılması ve yöntemlerin değerlendirilmesi amaçlanmıştır. İki yöntem kullanılarak başarılı birer tahmin modeli geliştirilmiştir. Modelleme sonucunda SARIMA ve Prophet yöntemlerinin MAPE değerleri sırasıyla 0,11 ve 0,13 olarak hesaplanmıştır.

🔖

Cite This Article

Küçüker, G., Araz, Ö. U. (2023). FORECASTING PUBLIC TRANSPORTATION PASSENGER DEMAND WITH SARIMA AND PROPHET METHODS. Endüstri Mühendisliği, Cilt: 34 Sayı: 3, 334–356. https://doi.org/10.46465/endustrimuhendisligi.1281645

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (23)

  1. Akgül, I. (2003). Zaman serilerinin analizi ve ARIMA modelleri. İstanbul: DER Yayınevi.
  2. Küçük Yılmaz, A., Kafalı, H., Işık, Y., Yaman, K., Özen, M., Küçük, F. (2019). Hava taşımacılığı. Eskişehir: Açıköğretim Fakültesi Yayını, No: 2204.
  3. Gerede, E., Orhan, G., Orhan, İ., Erdoğan, D., Ateş, S.S. (2019) Havayolu işletmelerinde operasyonel planlama. Eskişehir: Açıköğretim Fakültesi Yayını, No: 2649.
  4. Bozkurt, H. (2013). Zaman serileri analizi. Bursa: Ekin Yayınevi.
  5. Chicco, D., Warrens, M.J. & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput. Doi: https://doi.org/10.7717/peerj-cs.623
  6. Dantas, T., Oliveira, F. & Repolho, H. (2017). Air transportation demand forecast through Bagging Holt Winters methods. Journal of Air Transport Management, 59, 116-123. Doi: https://doi.org/10.1016/j.jairtraman.2016.12.006
  7. Halyal, S., Mulangi, R. H. & Harsha, M. M. (2022). Forecasting public transit passenger demand: with neural networks using APC data. Case Studies on Transport Policy, 10, 965–975. Doi: https://doi.org/10.1016/j.cstp.2022.03.011
  8. Jin, F., Li, Y., Sun, S. & Li, H. (2020). Forecasting air passenger demand with a new hybrid ensemble approach. Journal of Air Transport Management, 83. Doi: https://doi.org/10.1016/j.jairtraman.2019.101744
  9. Koç, İ. (2017). Türkiye’de iç hatlarda havayolu yolcu taleplerinin yapay sinir ağları kullanarak tahmini (Yüksek Lisans Tezi). İstanbul Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul.
  10. Kovačić, Z. (1995). The time series analysis. University of Belgrade. Faculty of Economics, Belgrade. Liyanage, S., Abduljabbar, R., Dia, H. & Tsai, P. (2022). AI-based neural network models for bus passenger demand forecasting using smart card data. Journal of Urban Management, 11, 365–380. Doi: https://doi.org/10.1016/j.jum.2022.05.002
  11. Navratil, M. & Kolkova, A. (2019). Decomposition and forecasting time series in business economy using Prophet forecasting model. Central European Business Review, 8(4). Doi: https://doi.org/10.18267/j.cebr.221
  12. Nurmi, N. (2021). Forecasting airport passenger traffic in the era of COVID-19 pandemic (Yüksek Lisans Tezi). Lappeenranta-Lahtı University of Technology, School of Business and Management, Finlandiya.
  13. Phyoe, S.M., Guo, R. & Zhong, Z.W. (2016). An air traffic forecasting study and simulation. Matter: International Journal of Science and Technology, 2(3), 55-69. Doi: https://doi.org/10.20319/Mijst.2016.23.5569
  14. Srisaeng, P., Baxter, G., Richardson, S. & Wild, G. (2015). A forecasting tool for predicting Australia’s domestic airline passenger demand using a genetic algorithm. Journal of Aerospace Technology and Management, 7(4), 476-489. Doi: https://doi.org/10.5028/jatm.v7i4/475
  15. Taylor, S.J. & Letham, B. (2017). Forecasting at scale. PeerJ Preprints. Doi: https://doi.org/10.7287/peerj.preprints.3190v2
  16. Wei, Y. & Chen, M. (2012). Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research, Part C 21, 148–162. Doi: https://doi.org/10.1016/j.trc.2011.06.009
  17. Wen, K., Zhao, G., He, B., Ma, J. & Zhang, H. (2022). A decomposition-based forecasting method with transfer learning for railway short-term passenger flow in holidays. Expert Systems with Applications, 189. Doi: https://doi.org/10.1016/j.eswa.2021.116102
  18. Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159 – 175. Doi: https://doi.org/10.1016/S0925-2312(01)00702-0
  19. Zhao, N., Liu, Y., Vanos, J. & Cao, G. (2018). Day-of-week and seasonal patterns of pm2.5 concentrations over the United States: time-series analyses using the Prophet procedure. Atmospheric Environment, 192, 116–127. Doi: https://doi.org/10.1016/j.atmosenv.2018.08.050
  20. Facebook, Prophet, Forecasting at scale. Erişim adresi: https://facebook.github.io/prophet/ (Erişim tarihi: 02/02/2023)
  21. Balıkesir Büyükşehir Belediyesi, Açık Veri Platformu, BTT-günlük taşınan yolcu sayıları. Erişim adresi: https://acikveri.balikesir.bel.tr/Veriler/ VeriSetiTabloGorunum?vsadi=asis-gunluk-yolcu(Erişim tarihi: 20/09/2022)
  22. T.C. Çevre, Şehircilik ve İklim Değişikliği Bakanlığı, Çevresel göstergeler. Erişim adresi: https://cevreselgostergeler.csb.gov.tr/ (Erişim tarihi: 04/04/2023)
  23. Balıkesir Büyükşehir Belediyesi, Otobüs ve güzergâh bilgisi. Erişim adresi: https://www.balikesirulasim.com.tr/hat/ERDEK-BANDIRMA (Erişim tarihi: 10/04/2023)