All Issue

2021 Vol.39, Issue 5

Article

Investigating Traveler’s Preference and Behaviors of Korea-Japan Undersea Tunnel between Busan and Fukuoka Using Interpretable Machine Learning Approaches

해석 가능한 기계 학습 접근법을 이용한 부산-후쿠오카간 한일해저터널 개통에 따른 수단 선택의 선호 분석에 관한 연구

Sanghyeon KO1
,
Dongwoo LEE2*
,
Hun Young JUNG3
고 상현1
,
이 동우2*
,
정 헌영3
1Transportation Engineering, Metropolitan Washington Council of Governments, Washington D.C. 20002, U.S.A.
2Assistant Professor, Department of Urban Policy and Administration, Incheon National University, Incheon 22012, Korea
3Professor, Department of Urban Engineering, Pusan National University, Busan 46241, Korea
1Metropolitan Washington Council of Governments 교통계획가
2인천대학교 도시행정학과 조교수
3부산대학교 도시공학과 교수
*Corresponding Author
31 October 2021. pp. 565-579
PDF XML Citation
Abstract

Followed by recent vibrant effort on the application of machine-based nonparametric approaches such as machine learning (ML), ML approaches have proven to be successful in many real-world applications. Despite their predictive performances, the acknowledged drawback of ML techniques is their lack of interpretable features that can be used to evaluate policy impacts. In this sense, this article aims to not only develop discrete choice modeling using ML techniques but also provide the useful insights about demystifying (i.e., interpreting) ML models. In particular, XGBoost, rule-based ensemble model combined with ML, is adopted to predict and understand mode choice behaviors related to Korea-Japan undersea tunnel high-speed train. XGBoost model notably possesses more interpretable algorithmic features than other ML models as well as high degree of predictive power for multi-level data—e.g., stated preference (SP) survey. Overall model estimates were accurated at 81% and also presented high accuracy for each model choice. To interpret users’ behaviors and preferences, variable importance (VI), variable contribution, and interactive partial dependence were estimated. The results of VI indicates that air mode, for instance, was affected by order of air fare, Fukuoka visit frequency, and Japan visit frequency, ferry mode was affected by order of Age, Willing to use tunnel, and Japan visit by air mode, and train mode was affected by train fare, age, and Japan visit frequency.

Keywords
discrete choice model
interpretation of machine learning
machine learning
random forest
user preference and behavior

컴퓨터 하드웨어 기술의 발전과 함께 기계 학습, 이른바 머신을 활용하여 반복적인 연산을 원활히 수행하고 데이터의 복잡한 패턴을 자율적으로 학습하는 머신러닝(Machine Learning)을 활용한 연구가 여러 분야에서 활발하게 이루어지고 있다. 최근 교통 분야에서도 다양한 머신러닝 방법론을 활용한 연구가 많이 활용되고 있지만, 높은 예측력에 비해서 정책 효과의 평가와 같은 부분에 있어서는 아직 그 해석의 가능성이 충분하지 못하다는 부분이 단점으로 지적되어왔다. 이러한 맥락에서, 본 연구는 머신러닝 기법을 활용한 수단선택 모형을 개발함과 동시에 머신러닝 모형 결과에 대한 분석 가능성을 제시하고자 하였다. 특히, 머신러닝 모형 중에서 rule-based의 앙상블 모형인 XGBoost 기법의 장점인 다계층적(multi-level) 자료에 대한 뛰어난 분석력과 모형 결과 해석 가능성에 대한 방안들을 활용하여 한일 해저터널을 통한 고속철도 여객 수요에 대한 수단선택 선호를 이해하고 예측하고자 하였다. 모형 전체의 예측 정확도는 81%로 높게 나타났으며, 각 수단 별로도 높은 수준의 선호 예측도를 보여주었다. 이른바 블랙박스라 불리는 학습된 머신러닝의 해석력을 높이고 정책적 활용도를 높이기 위해 변수 중요도와 변수 기여도, 그리고 평균 한계 변화율을 추정하였다. 항공 수단의 경우에는 항공 요금, 후쿠오카 방문 빈도, 일본 방문 빈도순으로 상대적 변수 중요도가 확인되었고, 고속 페리의 경우에는 이용자의 나이, 해저터널 이용 의사, 일본 방문 시 항공 이용, 고속철도의 경우에는 고속철도 운임, 연령, 일본 방문 빈도순으로 중요도를 확인할 수 있었으며, 각 변수의 변화에 따른 수단선택의 선호 변화에 대한 분석 또한 시각적으로 제시하였다.

키워드
수단선택모형
머신러닝 해석법
머신러닝
랜덤 포레스트
이용자 선호 및 행태
References
1
Ahmad N., Derrible S., Cabezas H. (2017), Using Fisher Information to Assess Stability in the Performance of Public Transportation Systems, Royal Society Open Science, 4(4), 160920. 10.1098/rsos.160920.
2
Ahmad N., Derrible S., Eason T., Cabezas H. (2016), Using Fisher Information to Track Stability in Multivariate Systems, Royal Society Open Science, 3(11), 160582. 10.1098/rsos.160582.
3
Akbarzadeh M., Memarmontazerin S., Derrible S., Salehi Reihani S. F. (2017), The Role of Travel Demand and Network Centrality on the Connectivity and Resilience of an Urban Street System, Transportation, 1-15. 10.1007/s11116-017-9814-y.
4
Chen T., Guestrin C. (2016), XGBoost: A Scalable Tree Boosting System, In Krishnapuram B., Shah M., Smola A. J., Aggarwal C. C., Shen D., Rastogi R. (eds.), Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, ACM. 785-794. 10.1145/2939672.2939785
5
Cho J., Kim C. (1998), A Comparative Study on the Commuter Mode Choice Behavior between Regions: Case of Seoul and Ilsan New Town, J. Korean Soc. Transp., 15(4), Korean Society of Transportation, 75-86.
6
Derrible S., Ahmad N. (2015), Network-Based and Binless Frequency Analyses, PLoS One, 10(11), e0142108. 10.1371/journal.pone.014210826529207PMC4631440
7
Friedman J. H. (2001), Greedy Function Approximation: A Gradient Boosting Machine, Annals of Statistics, 29(5), 1189-1232. 10.1214/aos/1013203451
8
Friedman J., Hastie T., Tibshirani R.(2001), The Elements of Statistical Learning, Springer Series in Statistics New York. 10.1007/978-0-387-21606-5
9
Ghasri M., Hossein Rashidi T., Waller S. T. (2017), Developing a Disaggregate Travel Demand System of Models Using Data Mining Techniques, Transportation Research Part A: Policy and Practice, 105, 138-153. 10.1016/j.tra.2017.08.020.
10
Golshani N., Shabanpour R., Mahmoudifard S. M., Derrible S., Mohammadian A. (2018), Modeling Travel Mode and Timing Decisions: Comparison of Artificial Neural Networks and Copula-Based Joint Model, Travel Behaviour and Society, 10, 21-32. 10.1016/j.tbs.2017.09.003.
11
Hagenauer J., Helbich M. (2017), A Comparative Study of Machine Learning Classifiers for Modeling Travel Mode Choice, Expert Systems with Applications, 78, 273-282. 10.1016/j.eswa.2017.01.057.
12
Hastie T., Tibshirani R., Friedman J. (2009), The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer Series in Statistics, New York. 10.1007/978-0-387-84858-7
13
Breiman L. (2001), Random Forests, Machine Learning, Kluwer Academic Publishers, 45, 5-32. 10.1023/A:1010933404324
14
James G., Witten D., Hastie T., Tibshirani R. (2013), An introduction to statistical learning, 112, Springer. 10.1007/978-1-4614-7138-7
15
Kim D. W., Bae Y. S. Lee Y. M. (1999), Analysis of travel modal choice and the temporal transferability for workers, Korean Journal of Applied Statistics, 17, 19-32.
16
Lee D. W., Derrible S. (2020), Predicting Residential Water Demand with Machine-Based Statistical Learning, Journal of Water Resources Planning and Management, American Society of Civil Engineers, 146(1), 04019067. 10.1061/(ASCE)WR.1943-5452.0001119
17
Lee D., Derrible S., Pereira F. C. (2018), Comparison of Four Types of Artificial Neural Network and a Multinomial Logit Model for Travel Mode Choice Modeling, Transportation Research Record, Journal of the Transportation Research Board, 2672, 101-112. 10.1177/0361198118796971
18
Lee D., Mulrow J., Haboucha C.J., Derrible S., Shiftan Y. (2019), Attitudes on Autonomous Vehicle Adoption using Interpretable Gradient Boosting Machine, Transportation Research Record, Journal of the Transportation Research Board. 10.1177/0361198119857953
19
Lee Y. H., Hong S. Y. (2019), Machine learning approach to the prediction of individual travel mode choices, Journal of the Korean Data, Information Science Society, 30(5), 1011-1024, http://dx.doi.org/10.7465/jkdi.2019.30.5.1011. 10.7465/jkdi.2019.30.5.1011
20
Lee Y. J., Min O. (2017), Comparative Analysis of Machine Learning Algorithms to Urban Traffic Prediction, Proc., 2017 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, South Korea. 10.1109/ICTC.2017.8190846
21
Lundberg S. M., Lee S. I. (2017), A Unified Approach to Interpreting Model Predictions, In Advances in Neural Information Processing Systems, edited by I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, 30, 4765-4674. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf.
22
Manski C. F. (1977), The structure of random utility models, Theor Decis 8, 229-254, 10.1007/BF00133443.
23
Pusan Metropolitan City (2018), Initial Research of Korea-Japan Undersea Tunnel, Pusan Metropolitan City.
24
Robert C. (2014), Machine Learning, a Probabilistic Perspective, Cambridge, MA, MIT Press 2014.
25
Schapire R. E. (2014), The strength of weak learnability, Mach Learn 5, 197-227. 10.1007/BF00116037.
26
Sekhar C. R., Madhu E. (2016), Mode choice analysis using random forest decision trees, Transportation Research Procedia, 17, 644-652. 10.1016/j.trpro.2016.11.119
27
Semanjski I., Gautama S. (2015), Smart City Mobility Application-Gradient Boosting Trees for Mobility Prediction and Analysis Based on Crowdsourced Data, Sensors, 15(7), 15974-15987. 10.3390/s15071597426151209PMC4541863
28
Wang F., Ross C. L. (2018), Machine Learning Travel Mode Choices: Comparing the Performance of an Extreme Gradient Boosting Model with a Multinomial Logit Model, Transportation Research Record, Journal of the Transportation Research Board, 2672, 35-45. 10.1177/0361198118773556
29
Wisetjindawat W., Derrible S., Kermanshah A. (2018), Modeling the Effectiveness of Infrastructure and Travel Demand Management Measures to Improve Traffic Congestion During Typhoons, Transportation Research Record, Journal of the Transportation Research Board, in press. 10.1177/0361198118791909
30
Xian-Yu J. (2011), Travel Mode Choice Analysis Using Support Vector Machines, ICCTP 2011: American Society of Civil Engineers, 360-371. 10.1061/41186(421)37
31
Xie C., Lu J., Parkany E. (2003), Work Travel Mode Choice Modeling with Data Mining: Decision Trees and Neural Networks, Transportation Research Record, Journal of the Transportation Research Board, 1854, 50-61. 10.3141/1854-06
32
Zhang Y., Haghani A. (2015), A Gradient Boosting Method to Improve Travel Time Prediction, Transportation Research Part C, Emerging Technologies, 58, 308-324. 10.1016/j.trc.2015.02.019
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 39
  • No :5
  • Pages :565-579
  • Received Date : 2021-04-27
  • Revised Date : 2021-05-14
  • Accepted Date : 2021-08-26
  • DOI :https://doi.org/10.7470/jkst.2021.39.5.565
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • scopus
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close