Inferring Trip Destination Purposes for Trip Records Collected through Smartphone Apps
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 149, Issue 2
Abstract
Rapid developments in smartphones and Global Positioning System (GPS) technology have provided a new method for travel data collection. People’s travel trajectories can be passively collected through smartphones with built-in GPS sensors and processed to infer important attributes of travel behavior such as trip destination purposes. This paper examines the feasibility of using discrete choice models and tree-based machine learning models for trip purpose inference. Using smartphone GPS trajectories and land-use data that are open-sourced for academic research, four models are developed to classify trip destination purposes into one of thirteen categories. The models include multinomial logit, mixed logit, random forest, and gradient boosting decision tree. Because the data set is significantly unbalanced with more than 50% of the trips being home or work trips, a two-stage modeling process is applied to identify home and work trips first and then subsequently to classify trips for the remaining discretionary purposes. The results show that both discrete choice models and machine learning models can achieve more than 70% prediction accuracies for home trips and work trips, but less than 30% prediction accuracies for most of the discretionary trip purposes. The discrete choice models can accurately reproduce the market share distribution of the trip purposes, but the machine learning models fail to do so. The results imply that as purely data-driven models, machine learning models may not be the best solution for trip purpose inference because they lack the theoretical background provided by microeconomics and human psychology that are essential in explaining people’s travel and activity choices.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The survey data used in this study are confidential and may only be provided with restrictions.
Acknowledgments
The authors would like to acknowledge the City Logger project team for data collection.
References
Bierlaire, M. 2020. A short introduction to PandasBiogeme. Technical Rep. No. TRANSP-OR 200605. Lausanne, Switzerland: Transport and Mobility Laboratory, ENAC, EPFL.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (4): 5–32. https://doi.org/10.1023/A:1010933404324.
Cui, Y., C. Meng, Q. He, and J. Gao. 2018. “Forecasting current and next trip purpose with social media data and Google places.” Transp. Res. Part C 97 (10): 159–174. https://doi.org/10.1016/j.trc.2018.10.017.
Data Management Group. 2016. Transportation tomorrow survey. Toronto: Univ. of Toronto.
DMTI Spatial Inc. 2019. “CanMap content suite.” Accessed March 15, 2021. https://mdl.library.utoronto.ca/collections/geospatial-data/dmti-canmap-content-suite-2019.
Ermagun, A., Y. Fan, J. Wolfson, G. Adomavicius, and K. Das. 2017. “Real-time trip purpose prediction using online location-based search and discovery services.” Transp. Res. Part C 77 (Jan): 96–112. https://doi.org/10.1016/j.trc.2017.01.020.
Faghih Imani, A., C. Harding, S. Srikukenthiran, E. J. Miller, and K. N. Habib. 2020. “Lessons from a large-scale experiment on the use of smartphone apps to collect travel diary data: The “City Logger” for the greater golden horseshoe area.” Transp. Res. Rec. 2674 (7): 299–311. https://doi.org/10.1177/0361198120921860.
Faghih Imani, A., J. Vaughan, and E. J. Miller. 2018. “Analysis of TTS 2016 trip rates.” In Travel modelling group. Toronto: Univ. of Toronto.
Friedman, J. 2001. “Greedy function approximation: A gradient boosting machine.” Ann. Stat. 29 (5): 1189–1232. https://doi.org/10.1214/aos/1013203451.
Google Developers. 2021. “Places API usage and billing.” Accessed May 10, 2021. https://developers.google.com/maps/documentation/places/web-service/usage-and-billing.
Hensher, D. A., and W. H. Greene. 2003. “The mixed logit model: The state of practice.” Transportation 30 (2): 133–176. https://doi.org/10.1023/A:1022558715350.
Kaur, H., H. S. Pannu, and A. K. Malhi. 2019. “A systematic review on imbalanced data challenges in machine learning: Applications and solutions.” ACM Comput. Surv. 52 (4): 79. https://doi.org/10.1145/3343440.
Kim, Y., A. Ghorpade, F. Zhao, F. C. Pereira, P. C. Zegras, and M. Ben-Akiva. 2018. “Activity recognition for a smartphone and web-based human mobility sensing system.” IEEE Intell. Syst. 33 (4): 5–23. https://doi.org/10.1109/MIS.2018.043741317.
Lee, R. J., I. N. Sener, and J. A. Mullins. 2016. “An evaluation of emerging data collection technologies for travel demand modeling: From research to practice.” Transp. Lett. 8 (4): 181–193. https://doi.org/10.1080/19427867.2015.1106787.
Meng, C., Y. Cui, Q. He, L. Su, and J. Gao. 2017. “Travel purpose inference with GPS trajectories, POIs, and geo-tagged social media data.” In Proc., 2017 IEEE Int. Conf. on Big Data, 1319–1324. New York: IEEE.
National Academies of Sciences, Engineering, and Medicine. 2014. Activity-based travel demand models: A primer. Washington, DC: National Academies Press.
Nguyen, M. H., J. Armoogum, J. L. Madre, and C. Garcia. 2020. “Reviewing trip purpose imputation in GPS-based travel surveys.” J. Traffic Transp. Eng. 7 (4): 395–412. https://doi.org/10.1016/j.jtte.2020.05.004.
Oliveira, M., P. Vovsha, J. Wolf, and M. Mitchell. 2014. “Evaluation of two methods for identifying trip purpose in GPS-based household travel surveys.” Transp. Res. Rec. 2405 (1): 33–41. https://doi.org/10.3141/2405-05.
Shen, L., and P. R. Stopher. 2013. “A process for trip purpose imputation from global positioning system data.” Transp. Res. Part C 36 (Sep): 261–267. https://doi.org/10.1016/j.trc.2013.09.004.
Stopher, P., C. FitzGerald, and J. Zhang. 2008. “Search for a global positioning system device to measure person travel.” Transp. Res. Part C 16 (3): 350–369. https://doi.org/10.1016/j.trc.2007.10.002.
Train, K. E. 2009. Discrete choice methods with simulation. New York: Cambridge University Press.
Yazdizadeh, A., Z. Patterson, and B. Farooq. 2019. “An automated approach from GPS traces to complete trip information.” Int. J. Transp. Sci. Technol. 8 (1): 82–100. https://doi.org/10.1016/j.ijtst.2018.08.003.
Information & Authors
Information
Published In
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Jan 27, 2022
Accepted: Sep 30, 2022
Published online: Nov 28, 2022
Published in print: Feb 1, 2023
Discussion open until: Apr 28, 2023
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Data collection
- Engineering fundamentals
- Freight transportation
- Geomatics
- Global navigation satellite systems
- Global positioning systems
- Infrastructure
- Logistics
- Methodology (by type)
- Model accuracy
- Models (by type)
- Research methods (by type)
- Surveying methods
- Traffic engineering
- Traffic models
- Transportation engineering
- Travel patterns
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Wenxiang Li, Yuliang Zhang, Yifan Chen, Longyuan Ding, Yijun Zhu, Xiqun (Michael) Chen, Multi-day activity pattern recognition based on semantic embeddings of activity chains, Travel Behaviour and Society, 10.1016/j.tbs.2023.100682, 34, (100682), (2024).