Travel demand forecasting using auto-regressive moving-average model (Case study: Qom-Tehran freeway)

Document Type : Original Article

Authors

1 Department of Civil Engineering, Islamic Azad University, Tehran North Branch

2 PHD candidate, transportation engineering, Imam Khomeini university

3 Department of Civil and Environmental Engineering Geotechnics, Roads and Transportation Specialty

4 Civil Engineering Department - Geotechnics and Road, Yazd university

5 Civil Engineering Department, Yazd University, Yazd, Iran

Abstract

The quality of traffic flow is one of the main characteristics of the transportation network, which is widely used in issues related to urban planning, route prioritization, reducing traffic congestion and travel time; Therefore, estimating the volume of traffic and predicting it in the future is one of the important issues for transportation planners. The problem of prediction requires modeling and determining the variables affecting changes in a particular phenomenon. In this research, travel demand is predicted using time series methods. The data required for this research have been prepared from the Roads and Transportation Organization. In this study, in order to build a model, two autoregressive processes and moving average have been used. Using the above methods, the amount of demand in the coming years up to the horizon of 1404 on the Qom-Tehran freeway is predicted. The results of the study showed that among the self-correlated and moving average models and the combination of two models, namely the self-correlated moving average, the third model has a more acceptable accuracy. The parameters of this model (4,5) ARMA were obtained. Also, the validity of the constructed model, based on the average value of absolute error percentage, was 0.047, R and R2 values were calculated 0.94 and 0.89, respectively, which shows that the model has acceptable accuracy.

Keywords


  1. Afandizadeh, A. Momenpour, “Analysis of demand for travel analysis with approach to neural network model and regression method, case study (Khalkhal-Ardabil)”, 14th International Conference on Transport and Traffic Engineering, 14 p. (in Persian), 2014.
  2. E. Kimes, “Transportation revenue management: could it work”, Journal of Revenue and Pricing Management, Vol. 4, No. 1, pp. 95-97, 2005.
  3. Misuk, “Modeling and forecasting hotel room demand based on advance booking information”, Tourism Management, Volume 66, pp. 62-71, 2017.
  4. Tiago, F. Dantas, C. Luiz, H. Oliveira, V. R. Miguel, “Air transportation demand forecast through Bagging Holt Winters methods”, Journal of Air Transport Management ,Vol. 59, pp. 116-123, 2017.
  5. Usman, T. Umer, S. Güven, “Forecasting performance of smooth transition autoregressive (STAR) model on travel and leisure stock index”, The Journal of Finance and Data Science, Vol. 4, Issue 2, pp. 90-100, 2018.
  6. Guo, T. Zhang, “A residual spatio-temporal architecture for travel demand forecasting”, Transportation Research Part C: Emerging Technologies ,115: 102639, 2020.
  7. F. Rossi, “Travel Demand Forecasting: Where are we and What are the Emerging Issues”, 2021.
  8. Liang, et al, “On region-level travel demand forecasting using multi-task adaptive graph attention network”, Information Sciences, 2022.
  9. Hamad, L. Obaid, “Tour-based travel demand forecasting model for a university campus”, Transport Policy, 117, pp. 118-137, 2022.
  10. Marc, P. B. Gelhausen, W. Dieter, “A new direct demand model of long-term forecasting air passengers and air transport movements at German airports”, Journal of Air Transport Management, Available online 12 April, p. 16 2018.
  11. Chyon, et al, “Time series analysis and predicting COVID-19 affected patients by ARIMA model using machine learning.”, Journal of Virological Methods, 301: 114433, 2022.
  12. Ghasemi, “Application of Neural Networks in Time Series Forecasting and Comparison with ARIMA Model”, Commercial Journal, pp. 88 to 110 (in Persian), 2001.
  13. Sarlak, “Comparative evaluation of AR, MA, ARMA, ARIMA time series models in predicting the stock index of Tehran Stock Exchange”, New research in management and accounting, second year, No. 3, pp. 130-145 (in Persian), 2017.
  14. Gupta, A. Kumar, “Two-step daily reservoir inflow prediction using ARIMA-machine learning and ensemble models”, Journal of Hydro-environment Research 45: 39-52, 2022.
  15. Nazeri Tohridi, “Evaluation of univariate, multivariate and time series compilations in predicting and estimating the average annual sediment load (Case study: Sistan River),” Environmental Erosion Research, pp. 52-70 (in Persian), 2016.
  16. Chakraborty, S. K. Sanyal, “Time-series data optimized AR/ARMA model for frugal spectrum estimation in Cognitive Radio.”, Physical Communication, 44: 101252, 2021.
  17. R. Sahbald, “Performance Comparison Genetic Planning and Time Series Pattern In the short-term forecast of passenger demand for Iranian Railways”, the Railway Research and Training Center No. 287, 6 p (in Persian), 2015.
  18. Afandizadeh, “Formulation of a Methodology for Assessing Parameters Effective on the Demand of Air Travel in Iran”, International Journal of Engineering Sciences of Iran University of Science and Technology, Vol. 19, p. 89-97(in Persian), 2008.
  19. Pourkazemi, M. Asadi, “Dynamic prediction of crude oil prices using artificial neural networks and with the use”, Master's thesis, faculty, Petroleum Systems of the Economic and Political Sciences of the Shahid Beheshti University, p. 73(in Persian), 2009.
  20. P. Karmy and S. Maldonado, “Hierarchical time series forecasting via support vector regression in the European travel retail industry”, Expert Systems with Applications 137: 59-73, 2019.
  21. Taymouri, “Designing the Mathematical Model for predicting demand for travel by train using time series of case studies: Khorasan axis”, Eighth Railway Transportation Conference, 15 p, 2006. (in Persian)
CAPTCHA Image