Modeling Freight Vehicle Type Choice using Machine Learning and Discrete Choice Methods

The choice of vehicle type is one of the important logistics decisions made by firms. The complex nature of the choice process is because of the involvement of multiple agents. This study employs a random forest machine learning algorithm to represent these complex interactions with limited information about shipment transportation. The data are from Commercial Travel Surveys with information about outbound shipment transportation. This study models the choice among four road transport vehicle types: pickup/cube van, single-unit truck, tractor trailer, and passenger car. The characteristics of firms and shipments are used as explanatory variables. SHAP-based variable importance is calculated to interpret the importance of each variable, and shows that employment and weight are the most important variables in determining the choice of vehicle type. The random forest model is also compared with the multinomial and mixed logit models. The model prediction results on the validation data are compared. The results show that random forest model outperforms both the multinomial and mixed logit model with an overall increase in accuracy of about 7.8% and 9.6%, respectively.

[1]  Abolfazl Mohammadian,et al.  Joint Model of Freight Mode and Shipment Size Choice , 2013 .

[2]  Chi Xie,et al.  WORK TRAVEL MODE CHOICE MODELING USING DATA MINING: DECISION TREES AND NEURAL NETWORKS , 2002 .

[3]  Geert Wets,et al.  Identifying Decision Structures Underlying Activity Patterns: An Exploration of Data Mining Algorithms , 2000 .

[4]  G. Jong.  Mode Choice Models , 2014 .

[5]  Tarek Sayed,et al.  Comparison of Neural and Conventional Approaches to Mode Choice Analysis , 2000 .

[6]  Sabreena Anowar,et al.  Joint model of freight mode choice and shipment size: A copula-based random regret minimization framework , 2019, Transportation Research Part E: Logistics and Transportation Review.

[7]  Joseph Y. J. Chow,et al.  Causal structure learning for travel mode choice using structural restrictions and model averaging algorithm , 2017 .

[8]  Naveen Eluru,et al.  Freight Mode Choice: A Regret Minimization and Utility Maximization Based Hybrid Model , 2018, Transportation Research Record: Journal of the Transportation Research Board.

[9]  Kriangkrai Arunotayanun,et al.  Taste heterogeneity and market segmentation in freight shippers’ mode choice behaviour , 2011 .

[10]  Praveen Edara,et al.  Traffic Flow Forecasting for Urban Work Zones , 2015, IEEE Transactions on Intelligent Transportation Systems.

[11]  M. Stinson,et al.  A joint model of mode and shipment size choice using the first generation of Commodity Flow Survey Public Use Microdata , 2017 .

[12]  Nedal T. Ratrout,et al.  Mode choice behavior of high school goers: Evaluating logistic regression and MLP neural networks , 2018, Case Studies on Transport Policy.

[13]  Tarek Sayed,et al.  FREIGHT MODE CHOICE MODELS USING ARTIFICIAL NEURAL NETWORKS , 1999 .

[14]  David A. Hensher,et al.  A comparison of the predictive potential of artificial neural networks and nested logit models for commuter mode choice , 1997 .

[15]  A. Samimi,et al.  A behavioral analysis of freight mode choice decisions , 2011 .

[16]  Robert Chapleau,et al.  Application of Machine Learning to Two Large-Sample Household Travel Surveys: A Characterization of Travel Modes , 2019 .

[17]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[18]  Fatin Zaklouta,et al.  Real-Time Traffic-Sign Recognition Using Tree Classifiers , 2012, IEEE Transactions on Intelligent Transportation Systems.

[19]  Jeppe Rich,et al.  A weighted logit freight mode-choice model , 2009 .

[20]  Nadir Yayla,et al.  The modeling of mode choices of intercity freight transportation with the artificial neural networks and adaptive neuro-fuzzy inference system , 2009, Expert Syst. Appl..

[21]  Philipp Probst,et al.  Hyperparameters and tuning strategies for random forest , 2018, WIREs Data Mining Knowl. Discov..

[22]  Mark Hickman,et al.  Copula-Based Joint Discrete–Continuous Model of Road Vehicle Type and Shipment Size , 2017 .

[23]  Rinaldo A. Cavalcante,et al.  A conceptual framework for agent-based modelling of logistics services , 2010 .

[24]  J. Holguín-Veras,et al.  An Experimental Economics Investigation of Shipper-carrier Interactions in the Choice of Mode and Shipment Size in Freight Transport , 2011 .

[25]  Bailing Zhang,et al.  Recognition of driving postures by contourlet transform and random forests , 2012 .

[26]  Tarek Sayed,et al.  Comparison of Adaptive Network Based Fuzzy Inference Systems and B-spline Neuro-Fuzzy Mode Choice Models , 2003 .

[27]  Julian Hagenauer,et al.  A comparative study of machine learning classifiers for modeling travel mode choice , 2017, Expert Syst. Appl..

[28]  Chuan Ding,et al.  An Analysis of Interstate Freight Mode Choice between Truck and Rail: A Case Study of Maryland, United States , 2013 .

[29]  Gavin Brown,et al.  Ensemble Learning , 2010, Encyclopedia of Machine Learning and Data Mining.

[30]  Ziyuan Pu,et al.  Comparing Prediction Performance for Crash Injury Severity Among Various Machine Learning and Statistical Methods , 2018, IEEE Access.

[31]  Muhamad Nazri Borhan,et al.  Analysis of transportation mode choice using a comparison of artificial neural network and multinomial logit models , 2017 .

[32]  Long Cheng,et al.  Applying a random forest method approach to model travel mode choice behavior , 2019, Travel Behaviour and Society.

[33]  Alípio Mário Jorge,et al.  Comparing state-of-the-art regression methods for long term travel time prediction , 2012, Intell. Data Anal..

[34]  Feifei Yang,et al.  Advancement of weather-related crash prediction model using nonparametric machine learning algorithms , 2020, SN Applied Sciences.

[35]  Agostino Nuzzolo,et al.  Urban freight demand forecasting: A mixed quantity/delivery/vehicle-based model , 2014 .