Work

Modeling intercity travel mode choice: Uncovering key factor interactions with machine learning

Year: 2025

Type: article

Abstract: Intercity travel mode choice refers to the decision-making process individuals or groups undergo when selecting a mode of transportation, such as car, train, bus, for journeys between cities. This choice is influenced by various factors, including travel cost, time, convenience, comfort, environmental impact, and personal preferences. The key challenge in intercity travel mode choice lies in balancing diverse traveler preferences, such as cost, time, and convenience, with sustainable and efficient transportation solutions. Accurately modeling and predicting these choices is essential for optimizing infrastructure and policy decisions. This paper presents a Nonlinear Effects of Key Factors on Intercity Travel Mode Choice through the Application of machine learning for Enhanced Predictive Modeling and Insights. The proposed technique is the Viscoelastic Constitutive Artificial Neural Networks (VCANN). The main objective of the proposed method is to explore the effects of the influencing factors on the intercity travel mode competition and evaluate their dynamic effects across the travel distance. Initially data is collected from Travel Preference Dataset. The proposed VCANN machine learning model was developed and implemented using the MATLAB platform to predict the most suitable travel mode based on travel time, cost, and convenience. Performance of proposed method examined utilizing performance metrics likes Accuracy, Precision, Recall, Travel Time, Convenience and Travel cost are analysed. The proposed VCANN method is compared with the existing methods such as, Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and Geographically weighted random forest regression (GWRFR).

Source: KSCE Journal of Civil Engineering

DOI: 10.1016/j.kscej.2025.100481

Authors: Loganayagan Shanmugam, Murugesan Ramasamy

Institution: Government College of Engineering, Erode

Language: English

Topic: Transportation Planning and Optimization

Subfield: Transportation

Field: Social Sciences

Domain: Social Sciences

SDGs: Industry, innovation and infrastructure, Sustainable cities and communities

Open Access status: gold

Estimated APC paid: $1,800