from 01.01.2019 until now
Saint-Petersburg, St. Petersburg, Russian Federation
Russian Federation
employee
UDC 656.072
UDC 656.027
This paper proposes a new method for forecasting passenger traffic using a combined model. Effective development of the regional transport sector depends on passenger traffic forecasting. Improving the quality of passenger transportation requires building logistics models and developing accurate forecasting methods. Passenger traffic forecasting is particularly relevant in the context of accelerated population and tourist growth, expanding city boundaries, and infrastructure development. High-quality passenger traffic forecasting enables efficient transport management and cost reduction. Accurate passenger traffic forecasting ensures comfortable conditions for passengers. To achieve accurate forecasting, this paper proposes a new combined method that combines the advantages of various forecasting models: gradient boosting, decision tree ensemble, and the Holt-Winters method. For the combined model, optimal weight selection is performed based on the model characteristics. The authors developed a Python program for the computational experiment. The results of the experiment showed a 15% increase in forecasting accuracy for the combined model compared to gradient boosting and a 19% increase compared to exponential smoothing.
passenger transportation, passenger flow forecasting, combined model, machine learning, efficiency improvement
1. Cheng Y., Li H., Sun S., Liu W., Jia X., Yu, Y. Short-term subway passenger flow forecasting approach based on multi-source data fusion // Information Sciences. – 2024. – T. 679. – S. 121109.
2. Cheng Z., Trépanier M., Sun L. Incorporating travel behavior regularity into passenger flow forecasting // Transportation Research Part C: Emerging Technologies. – 2021. – T. 128. – S. 103200.
3. Chuwang D. D., Chen W., Zhong M. Short-term urban rail transit passenger flow forecasting based on fusion model methods using univariate time series // Applied Soft Computing. – 2023. – T. 147. – S. 110740.
4. Hu Y. C. Air passenger flow forecasting using nonadditive forecast combination with grey prediction // Journal of Air Transport Management. – 2023. – T. 112. – S. 102439.
5. Jin K., Sun S., Li H., Zhang F. A novel multi-modal analysis model with Baidu Search Index for subway passenger flow forecasting // Engineering Applications of Artificial Intelligence. – 2022. – T. 107. – S. 104518.
6. Li H., Jin K., Sun S., Jia X., Li Y. Metro passenger flow forecasting though multi-source time-series fusion: An ensemble deep learning approach // Applied Soft Computing. – 2022. – T. 120. – S. 108644.
7. Li P., Wang S., Zhao H., Yu J., Hu L., Yin H., Liu Z. IG-Net: An interaction graph network model for metro passenger flow forecasting // IEEE Transactions on Intelligent Transportation Systems. – 2023. – T. 24. – №. 4. – S. 4147-4157.
8. Li W., Sui L., Zhou M., Dong H. Short-term passenger flow forecast for urban rail transit based on multi-source data // EURASIP Journal on Wireless Communications and Networking. – 2021. – T. 2021. – №. 1. – S. 9.
9. Lundaeva K. A., Saranin Z. A., Pospelov K. N., Gintciak, A. M. Demand Forecasting Model for Airline Flights Based on Historical Passenger Flow Data // Applied Sciences. – 2024. – T. 14. – №. 23. – S. 11413.
10. Luo D., Zhao D., Ke Q., You X., Liu L., Ma H. Spatiotemporal hashing multigraph convolutional network for service-level passenger flow forecasting in bus transit systems // IEEE Internet of Things Journal. – 2021. – T. 9. – №. 9. – S. 6803-6815.
11. Mulerikkal J., Thandassery S., Rejathalal V., Kunnamkody D. M. D. Performance improvement for metro passenger flow forecast using spatio-temporal deep neural network // Neural Computing and Applications. – 2022. – T. 34. – №. 2. – S. 983-994.
12. Tan Y., Li Y., Wang R., Mi X., Li Y., Zheng H., Wang Y. Improving synchronization in high-speed railway and air intermodality: Integrated train timetable rescheduling and passenger flow forecasting // IEEE Transactions on Intelligent Transportation Systems. – 2022. – T. 23. – №. 3. – S. 2651-2667.
13. Wang J., Wang R., Zeng, X. Short‐term passenger flow forecasting using CEEMDAN meshed CNN‐LSTM‐attention model under wireless sensor network // IET Communications. – 2022. – T. 16. – №. 10. – S. 1253-1263.
14. Wang X., Zhu C., Jiang J. A deep learning and ensemble learning based architecture for metro passenger flow forecast // IET Intelligent Transport Systems. – 2023. – T. 17. – №. 3. – S. 487-502.
15. Xue Q., Zhang W., Ding M., Yang X., Wu J., Gao Z. Passenger flow forecasting approaches for urban rail transit: A survey // International Journal of General Systems. – 2023. – T. 52. – №. 8. – S. 919-947.
16. Yi P., Huang F., Wang J., Peng J. Topology augmented dynamic spatial-temporal network for passenger flow forecasting in urban rail transit // Applied Intelligence. – 2023. – T. 53. – №. 21. – S. 24655-24670.
17. Yue M., Ma S. LSTM-based transformer for transfer passenger flow forecasting between transportation integrated hubs in urban agglomeration // Applied Sciences. – 2023. – T. 13. – №. 1. – S. 637.
18. Zhang Y., Chen Y., Wang Z., Xin, D. TMFO-AGGRU: A graph convolutional gated recurrent network for metro passenger flow forecasting // IEEE Transactions on Intelligent Transportation Systems. – 2023. – T. 25. – №. 3. – S. 2893-2907.
19. Zhang Y., Sun K., Wen D., Chen D., Lv H., Zhang Q. Deep learning for metro short-term origin-destination passenger flow forecasting considering section capacity utilization ratio // IEEE Transactions on Intelligent Transportation Systems. – 2023. – T. 24. – №. 8. – S. 7943-7960.
20. Zhang Y., Wang X., Xie J., Bai, Y. Comparative analysis of deep-learning-based models for hourly bus passenger flow forecasting // Transportation. – 2024. – T. 51. – №. 5. – S. 1759-1784.
