№1, 2024

SUPPORT VECTOR MACHINES FOR FORECASTING NON-SCHEDULED PASSENGER AIR TRANSPORTATION

Nadir Aghayev, Dashqin Nazarli

Forecasting non-scheduled passenger air transportation demand is essential for effective operational planning and decision-making. In this abstract, we explore the use of Gaussian Support Vector Machines (SVM) methods in forecasting non-scheduled passenger air transportation processes. SVM is a type of supervised machine learning algorithm that can be applied to various domains, including non-scheduled passenger air transportation. In classification and regression tasks, SVMs are considered especially useful. SVMs can be used to forecast passenger demand for specific routes or flights. By analysing historical data, including factors such as time of day, day of the week, etc., SVMs can help airlines estimate future passenger demand. This method is crucial for optimising ticket pricing and managing seat inventory. This research proposes the implementation of different Gaussian SVM methods for the forecasting of non-scheduled passenger air transportation (pp.3-9).

Keywords: Non-scheduled air transportation, Forecasting, Machine learning, Support vector machines, Gaussian kernel functions
References
  • ICAO. (2004). Manual on the Regulation of International Air Transport, Doc 9626, Second Edition. 
    http://www.icao.int/meetings/atconf6/documents/doc%209626_en.pdf
  • Xie, G., Wang, S., Zhao, Y., & Lai, K. K. (2013). Hybrid approaches based on the LSSVR model for container throughput forecasting: A comparative study, Applied Soft Computing, 13(5), 2232–2241.
    http://doi.org/10.1016/j.asoc.2013.02.002
  • Suykens, J. & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural Processing Letters, 9, 293–300.
    https://doi.org/10.1023/A:1018628609742
  • Heng, H. J., Zheng, B. Z., & Li, Y. J. (2009). Study of an SVM-based air cargo demand forecast model. International Conference on Computational Intelligence and Security (CIS’09), Beijing, China, December (pp. 53–55).
    http://doi.org/10.1109/CIS.2009.180
  • Shabri, A. (2015). Least square support vector machines as an alternative method in seasonal time series forecasting, Applied Mathematical Sciences, 9 (124), 6207–6216.
    http://doi.org/10.12988/ams.2015.58525
  • Huang, T. M., Kecman, V., & Kopriva, I. (2006). Kernel-based algorithms for mining huge data sets: supervised, semi-supervised, and unsupervised learning. New York: Springer.
    https://doi.org/10.1007/3-540-31689-2
  • Platt, J. (1999). Sequential Minimal Optimisation: A Fast Algorithm for Training Support Vector Machines. Technical Report MSR-TR-98–14.
  • Fan, R. E., Chen, P. H., & Lin, C. J. (2005). Working set selection using second order ınformation for training support vector machines, The Journal of Machine Learning Research, 6, 1871–1918.
  • Fan, R. E., Chen, P. H., & Lin, C. J. (2006). A study on SMO-type decomposition methods for support vector machines, IEEE Transactions on Neural Networks, 17:893–908.
    https://doi.org//10.1109/TNN.2006.875973
  • Lin, S. L. (2021). Application of machine learning to a medium gaussian support vector machine in the diagnosis of motor bearing faults, Electronics, 10, 2266.
    https://doi.org/10.3390/electronics1018226