Applying a random forest method approach to model travel mode choice behavior. (January 2019)

• Record Type: Journal Article
• Authors: Cheng, Long; Chen, Xuewu; De Vos, Jonas; Lai, Xinjun; Witlox, Frank
• Is Part Of: Travel behaviour and society. Volume 14(2019)
• Page Start: 1
• Page End: 10
• Publication Date: 2019-01
• Subjects: Travel mode choice -- Prediction performance -- Variable importance -- Random forest -- Nanjing (China); Transportation -- Periodicals; Population geography -- Periodicals; 303.48305
• DOI: 10.1016/j.tbs.2018.09.002
• Languages: English
• ISSNs: 2214-367X

Abstract

Highlights: A random forest method is used to analyze travel mode choices for enhanced prediction capability. We determined the optimal model parameters for a robust model specification. We compared the model performance with other approaches within the travel mode choice context. RF method has superior prediction accuracy, fast computation speed, and good interpretability. Abstract: The analysis of travel mode choice is important in transportation planning and policy-making in order to understand and forecast travel demands. Research in the field of machine learning has been exploring the use of random forest as a framework within which many traffic and transport problems can be investigated. The random forest (RF) is a powerful method for constructing an ensemble of random decision trees. It de-correlates the decision trees in the ensemble via randomization that leads to an improvement of forecasting and reduces the variance when averaged over the trees. However, the usefulness of RF for travel mode choice behavior remains largely unexplored. This paper proposes a robust random forest method to analyze travel mode choices for examining the prediction capability and model interpretability. Using the travel diary data from Nanjing, China in 2013, enriched with variables on the built environment, the effects of different model parameters on the prediction performance are investigated. The comparison results show that the random forest method performs significantly better in travel mode choice prediction for higher accuracy and less computation cost. In addition, the proposed method estimates the relative importance of explanatory variables and how they relate to mode choices. This is fundamental for a better understanding and effective modeling of people's travel behavior.