Panichpapiboon, Sooksan
Loading...
Preferred name
Panichpapiboon, Sooksan
Main Affiliation
Email
sooksan.pa@kmitl.ac.th
Now showing 1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, What Separates High-Performing Taxis From the Rest? A Case Study in Bangkok(2024-01-01)Taxi is a public transportation system widely used in many cities, including Bangkok, Thailand. It provides a convenient way for people to move around the city. However, past studies have shown that the Bangkok taxi system is highly inefficient. In fact, most taxis are vacant most of the time. Despite this fact, there are highly efficient taxis that outperform the others in terms of gaining higher revenue. Learning what these high-performing taxis do differently is essential to improving the overall system's efficiency. In this paper, we investigate the key factors that differentiate high-performing taxis from low-performing ones. Identifying these factors allows us to draw significant insights into improving each taxi's performance. Based on an analysis of real taxi trajectory data, this study shows that the two crucial factors that separate high-performing taxis from low-performing taxis are the passenger searching time and the ability to select less congested search routes. Thus, an effective solution needs to concentrate on improving these two factors. Enhancing other elements, such as passenger delivery time and delivery route, is much less effective and will not have any critical impact. Lastly, this paper presents an effective regression model for predicting the efficiency of an individual taxi based on its average vacant time and the proportion of time spent in congestion during a passenger search. The model performs well, with only an 8.28% error rate. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Characterizing the Distributions of Taxi Demand: Is Poisson the Right Model?(2024-01-01); Khunsri, KavepolStatistical distribution of taxi demand is essential for modeling the dynamics of taxi services. An accurate demand prediction not only helps the drivers lessen their searching time but also helps the passengers shorten their waiting time. Moreover, the temporal distribution of taxi demand is a critical component in traffic simulation. Obviously, a simulator needs to know how many new taxi pickup events to schedule after the others. In most studies, a poisson distribution is often used to model the temporal distribution of taxi pickups. However, this assumption has mostly been used without validation with empirical data. Therefore, it is unclear whether such an assumption is appropriate for modeling the statistical distribution of taxi demand. In this study, we characterize the temporal distribution of taxi pickups based on real taxi trip data from Bangkok, Thailand, and Chicago, IL, USA. It is shown that, in most cases, the poisson distribution is not suitable for modeling the temporal distribution of taxi pickups. On the contrary, this study demonstrates that a geometric distribution is more appropriate in modeling the temporal distribution of taxi pickups. To our knowledge, this has not been discovered in any prior studies.