Promoting carsharing attractiveness and efficiency: An exploratory analysis
Carsharing has grown significantly over recent years. Understanding factors related to the usage and turnover rate of shared cars will help promote the growth of carsharing programs. This study sets station-based shared car booking requests and turnover rates as learning objectives, by which generalized additive mixed models are employed to examine various effects. The results are: (1) stations with more parking spaces, longer business hours and fewer nearby stations are likely to receive more booking requests and have a higher turnover rate; (2) an area with a higher population density, a higher percentage of adults, a higher percentage of males, a greater road density, or more mixed land use is associated with more car usage and a higher turnover rate; (3) stations nearby transit hubs, colleges, and shopping centers attract more shared car users; (4) shared cars are often oversupplied at transit hubs; (5) both transit proximity and housing price present high degrees of nonlinearity in relation to shared car usage and turnover rates. Findings provide evidence for optimizing the usage and efficiency of carsharing programs: carsharing companies should identify underserved areas to initiate new businesses; carsharing seems more competitive in a distance to a bus stop between 1.2 km and 2.4 km, and carsharing is more effectively served in areas with constraints in accessing metro services; carsharing should be optimally discouraged at transit hubs to avoid the oversupply of shared cars; local authorities should develop a location-based and geographically differentiated quota in managing carsharing programs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration
Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradig…
Impacts of electric carsharing on a power sector with variable renewables
Electrifying the car fleet is a major strategy for mitigating emissions in the transport sector. As electrification cannot solve all negative externalities associated with cars, reducing the size of the car fleet would b…
Time SeriesComparing Neural and Attractiveness-based Visual Features for Artwork Recommendation
Advances in image processing and computer vision in the latest years have brought about the use of visual features in artwork recommendation. Recent works have shown that visual features obtained from pre-trained deep ne…
General Exploratory Bonus for Optimistic Exploration in RLHF
Optimistic exploration is central to improving sample efficiency in reinforcement learning with human feedback, yet existing exploratory bonus methods to incentivize exploration often fail to realize optimism. We provide…
Reinforcement LearningLightweight Facial Attractiveness Prediction Using Dual Label Distribution
Facial attractiveness prediction (FAP) aims to assess facial attractiveness automatically based on human aesthetic perception. Previous methods using deep convolutional neural networks have improved the performance, but …
Prediction