Modeling mode choice behaviors of commuters in car-dependent small country discrete choice models: A case study of Bahrain

Abstract

The aim of this study is to determine the factor affecting the mode choice of travelers in Bahrain, which presents a unique case due to its smaller area size and current dependence on cars. Hence, the need for promoting sustainable modes of transportation is critical for the country. The study used 3864 diverse data records extracted from traveler surveys. This data comprised of revealed preference responses. The variables considered in the modelling included traveler characteristics, and trip information. The logit model and the classification tree models were used to predict the mode choice, considering the currently available modes of transportation currently available (Car and Bus). The accuracy of the models was ascertained through a validation sample collected independently from the initial sample. Trip cost was the most influential factor on mode choice. Other important variables included direct and quick travel, accessibility, and convenience. In terms of model performance, the logit model demonstrated higher accuracy than the classification tree when modeling binary responses. The models and results of this study provide important conclusions for the transportation authorities, which can be utilized for developing and promoting sustainable transportation modes in Bahrain.

Keywords

• Mode choice
• Prediction
• Models
• Logit Model
• Classification Tree
• Behavior

References

1. Bhavsar, P., Safro, I., Bouaynaya, N., Polikar, R., & Dera, D. (2017). Machine learning in transportation data analytics. In Data Analytics for Intelligent Transportation Systems (pp. 283-307). Elsevier. google scholar
2. Chen, X., Liu, X., & Li, F. (2013). Comparative study on mode split discrete choice models. Journal of Modern Transportation, 21(4), 266-272. google scholar
3. Convery, S., & Williams, B. (2019). Determinants of transport mode choice for non-commuting trips: the roles of transport, land use and socio-demographic characteristics. Urban Science, 3(3), 82. google scholar
4. Daisy, N. S., Millward, H., & Liu, L. (2018). Trip chaining and tour mode choice of non-workers grouped by daily activity patterns. Journal of Transport Geography 69: 150-162. google scholar
5. Fawcett, T. (2006). Introduction to receiver operator curves. Pattern Recognit. Lett, 27, 861-874. google scholar
6. Geng, J., Long, R., & Chen, H. (2016). A review of the influencing factors of residents' travel mode choice. Journal of Beijing Institute of Technology (Social Sciences Edition), (5), pp. 1-9. google scholar
7. Ha, J., Lee, S., & Ko, J. (2020). Unraveling the impact of travel time, cost, and transit burdens on commute mode choice for different income and age groups. Transportation Research Part A: Policy and Practice, 141, 147-166. google scholar
8. Hadi, A. S., & Chatterjee, S. (2015). Regression Analysis by Example. John Wiley & Sons. google scholar

9. Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2, pp. 1-758). New York: springer. google scholar
10. Hillel, T., Bierlaire, M., & Jin, Y. (2019). A systematic review of machine learning methodologies for modeling passenger mode choice. Technical Report TRANSP-OR 191025. EPFL. google scholar
11. Hoel, L. A., Garber, Nicholas J., & Adek, A. W. S. (2011). Transportation infrastructure engineering a multimodal integration SI edition. google scholar
12. Hussain, H. D., Mohammed, A. M., Salman, A. D., Rahmat, R. A. B. O. K., & Borhan, M. N. (2017). Analysis of transportation mode choice using a comparison of artificial neural network and multinomial logit models. ARPN Journal of Engineering and Applied Sciences, 12(5), 1483-1493. google scholar
13. Kleinbaum, D. G., Kupper, L. L., & Muller, K. E. (1988). Odds ratio. In Applied regression analysis and other multivariate methods (pp. 104-118). PWS-Kent. google scholar
14. Kumar, C. P., Basu, D., & Maitra, B. (2004). Modeling generalized cost of travel for rural bus users: a case study. Journal of Public Transportation, 7(2), 59-72. google scholar
15. Kutner, M. H., Nachtsheim, C. J., & Neter, J. (2004). Applied linear statistical models (5th ed.). McGraw-Hill/Irwin. google scholar
16. Mahmood, H., Asadov, A., Tanveer, M., Furqan, M., & Yu, Z. (2022). Impact of oil price, economic growth and urbanization on CO2 emissions in GCC countries: asymmetry analysis. Sustainability, 14(8), 4562. google scholar
17. McCarthy, L., Delbosc, A., Currie, G., & Molloy, A. (2017). Factors influencing travel mode choice among families with young children (aged 0-4): a review of the literatüre. Transport Reviews, 37(6), 767-781. google scholar
18. Mendenhall, W., Beaver, R. J., & Beaver, B. M. (2013). Introduction to probability and statistics. Cengage Learning. google scholar
19. Modi, K. B., Zala, L. B., Umrigar, F. S., & Desai, T. A. (2011, May). Transportation planning models: a review. In National Conference on Recent Trends in Engineering and Technology, Gujarat India. google scholar
20. Mohammed, M., & Oke, J. (2023). Origin-destination inference in public transportation systems: A comprehensive review. International Journal of Transportation Science and Technology, 12(1), 315-328. google scholar
21. Mwale, M., Luke, R. & Pisa, N. (2022). Factors that affect travel behavior in developing cities: A methodological review. Transportation Research Interdisciplinary Perspectives, 16, 100683. google scholar
22. Nunnally, J. C., & Bernstein, I. H. (1994). Psychometric theory. New York: McGraw-Hill. google scholar
23. Ortûzar, Juan de Dios, & Willumsen, L. G. (2011). Modeling Transport (fourth edition), John Wiley & Sons, Ltd. google scholar
24. Pineda-Jaramillo, J. D. (2019). A review of Machine Learning (ML) algorithms used for modeling travel mode choice. Dyna, 86(211), 32-41. google scholar
25. Puan, O. C., Hassan, Y. A. H., Mashros, N., Idham, M. K., Hassan, N. A., Warid, M. N. M., & Hainin, M. R. (2019, May). Transportation mode choice binary logit model: A case study for Johor Bahru city. In IOP Conference Series: Materials Science and Engineering (Vol. 527, No. 1, p. 012066). IOP Publishing. google scholar
26. Ratrout, N. T., Gazder, U., & Al-Madani, H. M. (2014). A review of mode choice modeling techniques for intra-city and border transport. World Review of Intermodal Transportation Research, 5(1), 39-58. google scholar
27. Roy, S., Cooper, D., Mucci, A., Sana, B., Chen, M., Castiglione, J., & Erhardt, G. D. (2020). Why is traffic congestion getting worse?’ Decomposition of Contributors to Growing congestion in San Francisco: Determining the Role of TNCs. Case Studies on Transport Policy, 8(4), 1371-1382. google scholar
28. Sekhar, C. (2014). Mode choice analysis: the data, the models and future ahead. International Journal for Traffic & Transport Engineering, 4(3). google scholar
29. Sowjanya, D., Tahlyan, D., & Sekhar, C. R. (2014). Travel demand modeling for a metropolitan city. In International Conference on Recent Trends and Challenges in Civil Engineering (pp. 19-40). google scholar
30. Waghmare, A., Yadav, G., & Tiwari, K. (2022). Four step travel demand modeling for urban transportation planning. Sci. Eng. Technol., 5, 1254. google scholar
31. Waleed, S. (2019). The Ministry of Works is implementing a package of projects to reduce traffic congestion. Al Bilad News, Kingdom of Bahrain. Retrieved from http://www.albiladpress.com/news/2019/4016/bahrain/602413.html. Accessed on October 19, 2019. google scholar