• ETRI Journal
• /
• v.44 no.4
• /
• pp.624-640
• /
• 2022

Taxi-demand forecasting and hotspot prediction can be critical in reducing response times and designing a cost effective online taxi-booking model. Taxi demand in a region can be predicted by considering the past demand accumulated in that region over a span of time. However, other covariates-like neighborhood influence, sociodemographic parameters, and point-of-interest data-may also influence the spatiotemporal variation of demand. To study the effects of these covariates, in this paper, we propose three models that consider different covariates in order to select a set of independent variables. These models predict taxi demand in spatial units for a given temporal resolution using linear and ensemble regression. We eventually combine the characteristics (covariates) of each of these models to propose a robust forecasting framework which we call the combined covariates model (CCM). Experimental results show that the CCM performs better than the other models proposed in this paper.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.685-692
• /
• 2018

Busan city implemented 'taxi transfer discount system' since October 2017 in order to create for new demand taxis. However, due to the low transfer discount amount and limited payment method to prepaid cards, it is difficult to attain the aim. In this study, we investigated the usage status of taxi transfer discount system and the intention to use taxi transfer discount system according to the discount amount level. We established a model of intention to estimate demand of taxi transfer discount using ordinal logistic model. The results of analysis are as following. The critical reason for low usage was to limit taxi transfer discount payment methods to prepaid cards other than post-paid cards which is used for most transportation payment. It was found that the discount rate for taxi transfers was affected in order of payment method, the purpose of the travel, major transportation, frequency taxi use, age, transportation costs, and the discount of taxi transfers. Also, the taxi transfer discount could be expected to increase to 1,550 won based on the price elasticity of demand due to changes in taxi transfer discount rate.

• International Journal of Highway Engineering
• /
• v.14 no.3
• /
• pp.163-171
• /
• 2012

Demand Responsive Transit (DRT) services are becoming necessary as part of not only alternative transportation means for elderly and mobility impaired passengers, but also sustainable and flexible transportation options in urban area due to the development of communication technologies and Location Based Services (LBS). It is difficult to investigate the system performance regarding vehicle operational schemes and vehicle routing algorithms due to the lack of commercial software to support door-to-door vehicle simulation for larger area. This study proposes a simulation framework to evaluate innovative and flexible transit systems focusing on various vehicle routing algorithms, which describes data-type requirements for simulating door-to-door service on demand. A simulation framework is applied to compare two vehicle dispatch algorithms, Nearest Vehicle Dispatch (NVD) and Insertion Heuristic (IH) for real-time shared-taxi service in Seoul. System productivity and efficiency of the shared-taxi service are investigated, comparing to the conventional taxi system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.157-171
• /
• 2021

As smartphones spread and ICT technologies develop, taxi services have changed from hovering to platform-based calls and reservations. This has improved the mobility and accessibility of taxi users but caused problems, such as digital observing (no-responses to calls) for either short-distance services or services during the peak-demand periods. Digital Observing means ignoring and not accepting calls when they occur, which require improvement. Therefore, this study aims to derive measures to mitigate discrepancies in taxi supply and demand by adjusting the expected revenue of each taxi service using reinforcement learning based on the Taxi operation data. The results confirmed that the average complete response rate to calls would increase from 50.29% to 54.24% when incentives are applied, and an improvement of 5.86% can be achieved in short-distance sections of less than 5,000 won incentives. It is expected that the improvement will increase profitability for drivers, reduce the waiting time for passengers, and improve satisfaction with taxi services overall.

• Journal of Urban Science
• /
• v.7 no.2
• /
• pp.1-9
• /
• 2018

In this study, Analysis of DRT model and contribustion based on the case of local governments adopting the Demand Responsive Transit(DRT) in order to provide transportation in public transportation service weak area. Based on the case of Yeoju Area, the contribution of the DRT was analyzed. The DRT model was established as a fixed and call type model with taxi and bus transportation. Based on the results of the happy taxi service in Yeoju Area in 2016, the contribution of DRT was analyzed. According to the happy taxi performance of Yeoju city, it was introduced to 27 villages, and operated 4,188 times. And 9,111 people used it and Yeoju Area supported about 53 million Won. The contribution of local governments was analyzed in terms of local government, users, and social aspects. On local government aspects, we analyzed the budget cuts and complaints resolution. On the user aspects, we analyzed waiting time reduction, walking time reduction, travel time reduction, comfort, punctuality, and stability. On social aspects, we analyzed taxi and regional economy activation, and convenience of mobility.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.220-231
• /
• 2022

Building smart transportation services in urban cities has become a worldwide problem owing to the rapidly increasing global population and the development of Internet-of-Things applications. Traffic congestion and environmental concerns can be alleviated by sharing mobility, which reduces the number of vehicles on the road network. The taxi-parcel sharing problem has been considered as an efficient planning model for people and goods flows. In this paper, we enhance the functionality of a current people-parcel taxi sharing model. The adapted model analyzes the historical request data and predicts the current service demands. We then propose two novel online routing algorithms that construct optimal routes in real-time. The objectives are to maximize (as far as possible) both the parcel delivery requests and ride requests while minimizing the idle time and travel distance of the taxis. The proposed online routing algorithms are evaluated on instances adapted from real Cabspotting datasets. After implementing our routing algorithms, the total idle travel distance per day was 9.64% to 12.76% lower than that of the existing taxi-parcel sharing method. Our online routing algorithms can be incorporated into an efficient smart shared taxi system.

• Information Systems Review
• /
• v.18 no.4
• /
• pp.141-154
• /
• 2016

Mobile application is growing explosively with the advent of a new technology: smartphones. Mobile application is a new marketing channel and performs as a start-up platform. This study examines the effect of mobile application on the off-line market. Despite the continuous declining demand for taxi service, paradoxically, the supply of taxi service has increased. The taxi industry can be categorized into general taxi and call taxi. General taxi is accidental and inefficient because it has to search for its own passenger. As call taxi takes the request of a passenger, it is more efficient than general taxi. However, the current defective passenger-taxi driver matching system and insufficient taxi driver management hinder the development of the call taxi market. Differences in differences (DID) is an econometrical methodology that examines whether or not an event has meaningful influence. This research uses DID to investigate the effect of the Kakao taxi application on the call taxi industry. Furthermore, it examines the effect of major companies' reckless diversification, which is considered unethical behavior. The passengers of call taxi data from August 2014 to July 2015 and those of designated driving service data of the same period were collected as the control group.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.713-719
• /
• 2018

At present, Busan City has proposed various taxi industry development measures, but fundamentally there is a problem that the taxi supply is excessive compared to the demand. Therefore, this study tried to explore ways to activate the taxi reduction. We first identified problems with the taxi reduction program in Busan, and analyze thoughts of taxi operators and workers. As a result, difficulties in securing funding and lack of consent from a large number of stakeholders were identified as the first problem for current taxi reduction program. Second, both groups recognize the need for the taxi reduction, and taxi drivers are more willing to participate in the program. Third, the most important factor in determining to take the taxi reduction program was the amount of compensation. And to activate taxi reduction program, it is helpful for executives to improve their management conditions and for drivers to place reemployment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.57-65
• /
• 2022

Gyeongsangnam-do has been operating Bravo-taxi, a Gyeongnam-type DRT using taxi vehicles, since 2017 to guarantee the right of mobility for residents who live in areas lacking public transportation. This research investigated and analyzed changes in users' awareness over two years from beginning of Bravo-taxi operation in Gyeongsangnam-do, which started operating Bravo-taxis in 2017, targeting sites lacking public transportation. Through this study, the positive effects of taxi-type DRT were confirmed, such as improving the mobility of residents in areas underprivileged by public transportation, reducing required time for trips, and increasing preference for Bravo-taxis compared to existing buses. On the other hand, problems with the current Bravo-taxi system were also identified. In some areas, it was found that there were not enough coupons for Bravo-taxis, or in the case of Bravo-taxis operating at fixed times, the user's desired time and operating time did not match, resulting in lower satisfaction. The results of this research are expected to be utilized as basic data for service continuity of taxi-type DRT in operation by other local governments.

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.359-364
• /
• 2018

The purpose of this study is to investigate the phenomenon of users' experience of O2O transportation service - focus on the Kakao taxi. As a research method, first case study investigated characteristics of taxi app service in Korea and overseas O2O transportation service. Secondly, we conducted an in - depth interview with eight Kakao taxi users to understand the experience of using the taxi. As a result, we were able to derive two points that needed improvement. Firstly, the imbalance between supply and demand should be improved. Secondly, users should not be disadvantaged by the location disclosure. It is significant that this study suggests ways to improve domestic O2O transportation service through a taxi. It is expected that the follow up study will help improve the domestic O2O transportation service and improve the user experience.