Modeling Lane-Choice Behavior and Public Willingness to Pay for HOT Lanes: A Neural Network Approach

Abstract

This paper focuses on investigating public perception in the United Arab Emirates (UAE) towards the implementation of High-Occupancy Toll (HOT) lanes in major freeways. HOT lanes provide the UAE government with significant potential to enhance the transportation network through decline in motorway accidents, procuring additional revenues, decreasing the overall sector costs, as well as lessening the carbon footprint ensuing from this sector. However, the primary challenge encountered during the implementation of HOT lanes in the UAE is public perception and Willingness to Pay (WTP). A questionnaire-based survey was developed and circulated among the public in the UAE to deduce the public’s attitude towards the utilization of HOT lanes. The survey intended to capture the socio-economic, demographic, and commute-related characteristics of respondents, as well as their current knowledge of HOT lanes. The survey data were collected and processed to identify the features of the obtained sample. Comparative statistical and advanced numerical analyses, in the form of Linear Regression (LR) and Artificial Neural Networks (ANN) were conducted to model the relationships between different characteristics and the public’s WTP. Additionally, the significance of the factors affecting the WTP were ranked using Bayesian Networks. The results showed that monthly income was the most significant factor affecting public WTP followed by age, frequency of trips, employment status, peak hour traffic, and emirate of residence. Prediction equations generated from ANN and LR, utilizing the most significant factors, indicated that ANN had significantly higher accuracy and lower MSE compared to linear regression. Overall, this study could significantly help decision-makers for future transportation systems improvement.