Online Car-hailing Service Research Articles

Exploring the built environment impacts on Online Car-hailing waiting time: An empirical study in Beijing

Waiting time is a critical metric for evaluating the quality of online car-hailing services, with studies indicating a close association between Online Car-hailing waiting time (CWT) and the urban built environment (BE). Points of interest (POI) data is widely utilized to characterize the built environment. However, quantifying the proper combination or spatial relationships between different types of POIs to capture the functional features of the built environment within a region poses a challenge. This paper proposes a framework for analyzing built environment characteristics based on a semantic probabilistic topic model utilizing Latent Dirichlet Allocation, demonstrating that integrating the building area of POIs along with the travel activity intensity at their respective locations enables a more precise identification of regional functions. Moreover, while some studies have explored the correlation between the built environment and waiting time, few have evaluated the nonlinear interactions between them. On this foundation, employing the machine learning technique XGBoost model in conjunction with online car-hailing order data, we probe the relationship between the built environment and waiting time. The research indicates that CWT is comprehensively affected by multiple factors. Taking weekday evening peak period as an example, the CWT of Central-urban area, where has dense commercial and office land use, positively correlated with commercial and office topics, while negatively correlated with educational, residential, leisure and healthcare topics, leading to a longer CWT in the Central-urban. In addition, the interaction between BEs can weakens their individual effects on CWT. A higher degree of job-residence balance can mitigate the negative impact of residential and office topics on increasing CWT, particularly in Intermediate-urban areas. Additionally, BE topics may also suppress the positive effect of road density on reducing CWT. The relationship between the BE and CWT exhibits threshold effects and a V-shaped relationship, indicating that the BE is significantly associated with CWT only within specific ranges. This correlation also exhibits a gradient pattern from the Central-urban to the Sub-urban, especially concerning office and residential topics. These outcomes elucidate the salient ranges of the built environment that exert substantial impacts on waiting time, informing strategic planning for online car-hailing dispatch and urban development to augment passenger travel satisfaction.

Optimizing Customized Bus Lines Considering Users' Transfer Willingness under Cooperative and Competitive Relationship between Metro and Online Car-hailing

In the context of ‘carbon peak’ and ‘carbon neutrality’, coordinating individual travel demand through multi-modal transportation and guiding travelers towards new shared public transportation (PT) modes is increasingly important. In this paper, we analyze the competitive and cooperative relationship between online car-hailing (OCH) services and metro systems in Nanning, China, and conduct aquestionnaire survey among different types of OCH users. A mixed choice model that considers psychological latent variables is constructed to investigate OCH users’ attitudes and cognitions toward customized buses (CBs). An improved adaptive Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is proposed to identify potential carpooling station sets, and a hybrid genetic-ant colony algorithm (GACA) is designed to solve bi-level programming model for CB line optimization. Case study results indicate an 83.8% overall transfer rate from OCH users to CBs, with the optimized scheme achieving a 69.68% reduction in carbon emissions.

Service quality improvement strategies of online car-hailing based on SPC-PCN method

Online car-hailing service is practicing the concept of sharing, bringing new energy and convenience to the transportation market. However, with its rapid development, service issues have become increasingly prominent, and improving service quality is the key to the sustainable growth of the online ride-hailing industry. Microblog, as a major online platform for gathering public views, have become one of the significant media for publishing and disseminating information nowadays, which also contains numerous views of online taxi users on online taxi services. Aiming at the deficiency of online car-hailing service under microblog public opinion, this paper integrates Service Profit Chain (SPC) and Process Chain Network (PCN) from the perspective of service management. Firstly, a crawler program is used to collect the Internet Word of Mouth data related to online taxi. Then, a BERT text classification model is constructed to roughly classify the data, and the accuracy of this model is tested to 94.54 %. Afterwards, layer segmentation is implemented based on SPC and CatBoost. Besides, a series of problems in the current online taxi service, such as poor attitude of drivers, unsafe driving, and inefficient communication with the customer service staff, have been identified by using sentiment analysis and frequent mining methods. Finally, PCN analysis is used to optimize the online taxi service, proposing strategies such as setting a reservation reminder function, building a dynamic feedback mechanism, and establishing a contact point for lost and found items. The new SPC-PCN online taxi service system constructed in this paper is vital for service quality optimization, and can also promote the sustainable growth of the online taxi market.

Exploring the Influence of the Built Environment on the Demand for Online Car-Hailing Services Using a Multi-Scale Geographically and Temporally Weighted Regression Model

Online car-hailing is gradually shifting towards a predominant use of electric vehicles, a change that is advantageous for developing a sustainable society. Understanding the patterns of changes in online car-hailing travel can assist transportation authorities in optimizing vehicle dispatching, reducing idle rates, and minimizing resource wastage. The built environment influences the demand for online car-hailing travel. Previous studies have commonly employed the geographically weighted regression (GWR) model and the geographically and temporally weighted regression (GTWR) model to examine the relationship between the demand for online car-hailing trips and the built environment. However, these studies have ignored that the impact range of the built environment also varies with time and space. To fully consider the variations in the impact range of the built environment, this study established multi-scale geographically and temporally weighted regression (MGTWR) to examine the spatiotemporal impacts of urban built environments on the demand for online car-hailing travel. An empirical study was conducted to assess the effectiveness of the MGTWR model using point of interest (POI) data and online car-hailing order data from Haikou. The evaluation indicators showed that the MGTWR model has higher fitting accuracy than the GTWR model. Moreover, the impact of each type of POI on the demand for online car-hailing travel was analyzed by examining the temporal and spatial distribution of the regression coefficients. Additionally, we observed that transport facility POIs and healthcare service POIs exerted the most pronounced influence on the demand for online car-hailing. In contrast, the impact of shopping service POIs and catering service POIs was relatively weaker.

Evaluating the Nonlinear Impacts of Built Environment on Online Car-Hailing: Focus on the Whole Day

Understanding the relationship between the built environment and online car-hailing travel behavior can greatly influence sustainable urban development. These complex impacts are not fully understood from a whole-day perspective. This paper took the central urban area of Nanning, China as a case study, and analyzed the data of 1,154,759 online car-hailing service orders collected by the Nanning Information Center over the course of a week. Thiessen polygons based on road networks were used to divide the research area. A partial dependence plot and random forest regression were used to examine the nonlinear impacts of the built environment (home-work attributes, traffic facility attributes, land use, and diversity) on online car-hailing trip demand throughout the day. The results show that the built environment elements that affect the demand for online car-hailing differ at different times of the day and that they have different ranges of influence. For example, residential areas play an important role in the commuter period for demand with a contribution rate of 33.2%, while the contribution rates for the remaining periods are less than 5%. In the whole day, cultural services, health services, leisure sports services, and catering services are important factors. And if there are enough training institutions to form a separate trading area within a city, this will have a profound impact on travel demand. In comparison to subway stations, bus stations contribute more to the demand. The study results will assist the government in improving urban transportation coordination.

Mobile Charging Station Placements in Internet of Electric Vehicles: A Federated Learning Approach

In Internet of Electric Vehicles (IoEV), mobile charging stations (MCSs) can be deployed to complement fixed charging stations. Currently, the strategy of MCSs is to move towards the EVs with insufficient energy (IEVs) only after being requested, which is not efficient. However, similar to online car-hailing services, more IEVs could be charged and the charging expenses could be reduced if idle MCSs can actively move towards the potential charging positions. In this paper, the problem of placements of idle MCSs in an IoEV is investigated in order to enhance the proportion of charged IEVs and reduce the charging expenses of IEVs. To this end, we propose a Federated Learning based Placement Decision Method of Idle MCSs (FL-PDMIM) to help the idle MCSs to predict the future charging positions, by exploiting the historical routes of MCSs which contain rich information regarding the charging demand of IEVs. In the proposed framework, the historical routes are trained locally by each MCS, and then the local model parameters and charging records are periodically uploaded to an edge server for a global parameter aggregation. Then, idle MCSs decide their placements according to the predicted charging positions (potential charging positions). The training time can be largely shortened, because the distributed learning on each MCS is executed in parallel. Extensive simulations and comparisons demonstrate the performance superiority of FL-PDMIM. Specifically, with the proposed federated learning-based predictions, the waiting time of IEVs to be served can be significantly shortened, and FL-PDMIM enhances the proportion of charged IEVs and reduces the charging expenses of IEVs effectively.

The Car-Purchasing Intention of the Youth in the Context of Online Car-Hailing: The Extended Theory of Planned Behavior

Online car-hailing services have become an integral part of people’s daily travel in China. Considering that young people are the major consumer group in car purchases, it is worth investigating how the experience of online car-hailing services affects their intention to purchase a car. Based on the extended theory of Planned Behavior, this study found that the factors that negatively impact the car purchase intention of the youth are firstly the public transportation service quality, followed by the risks of private cars, and finally the online car-hailing services quality. Elevating the convenience and comfort of public transportation is conducive to reducing car purchasing intention. The indirect effect of online car-hailing services on car purchase intention is greater than its direct effect, and the most important factor is attitude. The car purchase intention is significantly heterogeneous across age and annual household income groups. Improving the convenience of public transportation will reduce the car purchase intention of people in the early youth. For middle and later youth, providing demand-responsive transit for important individuals to meet their diverse needs can reduce car purchase intention. As for online car-hailing services, youth care most about their convenience and comfort and worry most about their safety. Providing better online car-hailing services can reduce the car-purchasing intention of youth.

The GHG Emissions Assessment of Online Car-Hailing Development under the Intervention of Evaluation Policies in China

To assess the impact of the online car-hailing services on the environment in China, in this paper, we develop a model to evaluate greenhouse gas (GHG) emissions and emission reduction during the production and use of car-hailing, as a result of increased online bookings. Since energy use differs according to type of vehicle, this paper also contains different scenarios that depict degrees in the regulation stringency according to the Chinese Preliminary Rules on the Management of Online Car-Hailing, regional differences, and development of electric vehicles. The results show that, under the three different scenarios, the online car-hailing service would have the highest GHG emissions of 325, 413, or 160 MtCO2 and the highest reduction in emissions of 19.46, 25.1, or 9.48 MtCO2 by 2030. The government needs to encourage the development of online car-hailing to reduce the purchase of private cars, avoid compulsory actions to shut down online car-hailing platforms, and mandate that only electric vehicles (EVs) can be used for online car-hailing.

A Practical Fog-Based Privacy-Preserving Online Car-Hailing Service System

Aiming for minimizing passengers waiting time and vehicles vacancy rate, online car-hailing service systems with fog computing has been deployed in various scenarios. In this paper, we focus on addressing the security and privacy issues in such a promising system by customizing a new cryptographic primitive to provide the following security guarantees: (1) private, fine-grained and bilateral order matching between passengers and drivers; (2) authenticity verification of passengers orders in the form of ciphertext, and (3) temporal assurance of passengers’ ciphertext orders. To the best of our knowledge, no previous system has been designed to meet all three requirements. Existing cryptographic primitives (including forward/puncturable encryption (FE/PE) and attribute based matchmaking encryption (AB-ME)) may be leveraged to partially address some of challenges, but there lacks a comprehensive solution. Moreover, the integration of existing works is hampered by the heterogeneity and the weak coupling between distinct cryptographic primitives. As a result, it is infeasible to directly exploit them for the online car-hailing service. To tackle that, we put forward a new cryptographic primitive called Fine-grained Puncturable Matchmaking Encryption (FP-ME) by modifying AB-ME and incorporating PE technology. FP-ME can simultaneously implement fine-grained and bilateral order matching, the authenticity of passengers orders, and meeting the time constraint of passengers orders. We formalize the adversarial models for the proposed FP-ME and then present rigorous security analysis to prove the security of the proposed system. Additionally, we study performance of the system via simulations to demonstrate its practicability and effectiveness in the real-world applications.

Contribution of China's online car-hailing services to its 2050 carbon target: Energy consumption assessment based on the GCAM-SE model

As online car-hailing services in China have matured and gained legitimacy as a traffic business activity supported by national policies, they have exceeded the expected speed of development. This paper estimates the extent to which online car-hailing services will affect China's energy consumption and carbon emissions under several scenarios. To weigh the substitution effect of online car hailing toward China’s 2050 environmental goals, a Global Change Assessment Model 4.0-Sharing Economic (GCAM-SE) is used to analyze and associated government policy. Results indicate that by 2050 China's online car-hailing will achieve emission reductions of 8.36, 14.51, and 95.66 MTCO2 under, respectively, strict, moderate, and non-strict levels of the national Preliminary Rules on the Management of Online Car Hailing (PRMOCH). In 2015–2033, strict PRMOCH can better reduce energy consumption and carbon emissions by controlling the number of online car-hailing services, as compared to non-strict PRMOCH. After 2033, online car-hailing services will automatically realize the emission reduction function, whereas in this study's scenarios 1 and 2, the PRMOCH will hinder realizing car hailing's intended emission reduction function. These results strongly suggest the policy for online car hailing will be counterproductive unless policy makers consider the difference between the PRMOCH validity period and invalidity period.

Exploring Taxi Demand Distribution of Comprehensive Land-Use Patterns Using Online Car-Hailing Data and Points of Interest in Chengdu, China

With the rapid advance of urbanization, land-use intensity is increasing, and various land-use forms gather to form comprehensive land-use patterns. Traffic demand shows variability and complexity under comprehensive land-use patterns. Accurate analysis of traffic demand in urban transportation is the key to active traffic control and road guidance. Researchers have widely studied the relationship between traffic demand and land-use patterns, while land-use intensity is ignored when classifying land-use patterns, and the traffic demand distribution in each land-use pattern is not studied specifically. Taxi is a flexible public mode in urban areas, and taxi demand is an important component in analyzing traffic demand and identifying traffic hotspots in cities. This paper explores taxi demand distribution of comprehensive land-use patterns using online car-hailing data and points of interest (POI) in Chengdu, China. The demand-driven traffic analysis zones are developed by clustering origin–destination points of online car-hailing services. Using POI data, comprehensive land-use patterns are classified with land-use forms and land-use intensity. The K-shape algorithm is adopted to extract the typical taxi demand distribution in each comprehensive land-use pattern. Finally, two indicators, total taxi demand (TTD) and taxi demand difference (TDD), are computed and further analyzed. Results show that taxi demand distribution is still differential even under the same land-use pattern. Three land-use patterns whose average hourly taxi demand reaches about 300 vehicles per square kilometer have the largest TTD and most uneven TDD. The findings can support traffic management, land-use combination, and land-use adjustment to avoid concentrated taxi demand and mismatched TDD.

Why they don't choose bus service? Understanding special online car-hailing behavior near bus stops

People are more likely to choose to take a bus for travel theoretically if both the origin and destination are located near bus stops. However, many of these trips are now replaced by online car-hailing service in China. This study makes the first attempt to look into this special hailing behavior by conducting a contrast analysis between hailing trip and its corresponding bus journey with the same origin and destination. We proposed an identification approach to classify the special hailing trips into four types of hailing behaviors with various hailing willingness. Structural equation modeling is then used to explore the impacts of land use characteristics, features of transport facilities and hailing ridership characteristics on the performance of special hailing behavior. Based on the results, 10.86 percent of special hailing trips have origins and destinations that are located within 100 m distance of the bus stop. Imbalance travel demand for special hailing at different periods of the day indicates the time-varying characteristic, which reaches its highest level in the afternoon. Especially through the major mobility trends of these trips, the spatial patterns of special hailing behavior can be divided into two regimes (i.e. urban and suburban areas) corresponding to the agglomeration area of varied social activities and residential areas. The generalized travel costs of bus and online car-hailing reflect the hailing willingness of travelers to some extent. People face the tradeoff between the two travel modes and tend to choose instead to use online car-hailing in different situations, and the SEM results support this. Notably, the accessibility of bus stops and users' bus travel experience show significant negative effects on special hailing behavior, and the need to transfer during a bus journey can particularly influence a traveler's initiative to take a bus. The findings provide insights into the special online car-hailing usage patterns at bus stop level and its role in urban transport, which can support accurate planning and upgrading of sustainable public transit to increase competitiveness at the big picture.

A multi-sided market of personal data resource allocation: An empirical study of China’s car-hailing platform

The current rapid development of online car-hailing services creates a serious challenge to the existing paradigm of market governance and antitrust policy. However, the debate on the market structure of the car-hailing platform requires more empirical evidence to uncover its functions. This research adopts an interdisciplinary methodology based on computer science and economics, and including software reverse engineering tools applied to the interoperability of the terminal application and resource allocation model, to demonstrate the topological market structure of personal data resources allocation in China’s car-hailing industry. Within the discussion of the hybrid nature of technology and economy, the analysis results clearly show that China’s car-hailing platform services present a multi-sided market structure when seen from the perspective of personal data resource allocation. Personal data resource (PDR), that is considered an essential market resource, is applied as an asset transferred unhindered between platforms via the application programming interface, and thus, creating a new market allocation mechanism. The connection between the car-hailing platforms and social media platforms is an essential aspect of the market competition in the domain. As applications of online platforms increase in the global context, this research offers a new perspective in personal data resource allocation with implications for the governance of the platform economy.

How social distance affects the intention and behavior of collaborative consumption: A study based on online car-hailing service

In recent years, advances in mobile communications technology have enabled collaborative consumption or product sharing between consumers on a large scale. Unlike traditional consumption, collaborative consumption is based on collaboration among individuals, so that the decision-making mechanisms of individual consumers may be different from those in traditional consumption scenarios. The current study focuses on how the social distance between consumers and drivers affects collaborative consumption intention in the case of online car-hailing services. In this study, the theory of planned behavior (TPB) is used as the foundational framework, and we innovatively add the concept of social distance to the TPB to form a new, and integrated model. We test the model based on data collected from 315 online car-hailing users. The results shows that behavioral attitudes, subjective norms, and perceived behavioral control, positively influence collaborative consumption intention and behavior. More interestingly, we find that social distance has both direct and indirect impacts on collaborative consumption intention: The greater the social distance, the lower the collaborative consumption intention. Moreover, social distance also moderates the influence of subjective norms and perceived behavioral control on collaborative consumption intention. To be specific, the influence of subjective norms and perceived behavioral control on collaborative consumption intention is weakened when consumers perceive less social distance. The results suggest that the integrated model has a stronger explanatory power on collaborative consumption behavior. This study enhances the traditional TPB model and offers insight into promoting collaborative consumption in the context of the sharing economy.

Short-term demand forecasting for online car-hailing using ConvLSTM networks

This paper used the previous data of online car-hailing orders in Haikou provided by Didi Chuxing GAIA Initiative to predict the short-term demand for online car-hailing service. This paper contains two main steps. The first step is about converting online car-hailing demand for images that contains spatiotemporal feature of online car-hailing orders. This paper draws a picture every 72 min from 2017∕5∕8 to 2017∕8∕8, with a total of 1,840 binary vector images. The second step is to employ the deep learning method of a Conv-LSTM neutral network to the image for online car-hailing demand prediction. Conv-LSTM has excellent image prediction properties, so it is ideal for predicting such binary vector figures with spatiotemporal information. After learning the first 1460 images, the last 380 images were simulated, predicted and tested. Finally, the simulation results of the last 20 images were taken as the effect of the model. Our result shows that the Conv-LSTM neutral network can train the model with a reasonable output and is suitable for short-term forecasting network ride-hailing demand forecast with spatiotemporal feature information. By comparing five different training session times, it can be seen that when the number of training session reaches 30, the model reaches an optimum. Reasonable prediction results can provide data support for vehicle dispatching and distribution, solve problems such as energy waste and traffic congestion caused by asymmetric supply and demand, and maximize the interests of passengers, drivers and ride-hailing platforms.

Online Car-hailing Service Quality Evaluation Based on BP Neural Network

In order to reduce the subjectivity and make sure the online car-hailing evaluation results more authentic and credible, an evaluation index system is constructed from five dimensions of the safety, cost, time, reliability and empathetic, and then a BP neural network model is proposed to solve it. Through the supervised model training of SP survey data, the maximum error between the network output and the actual results no more than 3.68%, which can meet the requirements of online car-hailing service quality evaluation. Finally, a mathematical statistical analysis method is proposed to comprehensive evaluate the online car-hailing service quality. The results show that the evaluation index system is scientific and reasonable, and the model can effectively improve the objectively of the evaluation results and reflect the quality level of online car-hailing service.

Supervision of the Default Risk of Online Car-Hailing Platform from an Evolutionary Game Perspective

Online car-hailing services are becoming a key component of the public transportation system, despite there being some certain risks, especially default risk. Turning to the evolutionary game method, this research constructed an evolutionary game model of online car-hailing platform, and then analyzed the equilibrium state of three scenarios (i.e., no supervision, internal supervision of platform enterprises, and external supervision of regulators), followed by carrying out a simulation. The results showed that to realize the evolution stability strategies (ESS) of default risk control, a strong credit constraint or the establishment of a coordinated supervision mode with appropriate intensity are needed. On this basis, this research puts forward the coordinated “platform enterprise + regulator” supervision mode, as well as the following four specific strategies: Promoting the construction of a credit system, strengthening the construction of laws and regulations, establishing a service process control mechanism, and introducing innovative regulatory means.

Impact of Value Cocreation on Customer Satisfaction and Loyalty of Online Car-Hailing Services

The theory of value cocreation has been applied widely in the research of a lot of fields, including the field of travelling. At present, online shared cars have become one of the main modes of travel for urban residents, which have caused people to think about the quality of its service and its customer satisfaction. The objective of this research is to explore the impact of value cocreation by both the platform and drivers on customer satisfaction and user loyalty using Didi as an example. We propose five factors that can measure value cocreation behaviors, among which system availability and privacy count for value cocreation by online platform and perceived usability, consistency and competence are indicators of value cocreation by drivers. In total, 338 questionnaires were distributed to retrieve data and further investigate the users’ willingness of taking shared-cars, their satisfaction and loyalty towards Didi in order to help the corporate progress. This study provides suggestions for service-oriented corporations related to the sharing economy in order to enhance their user loyalty as well as improve their management ability.

A Convolutional Long Short-Term Memory Neural Network Based Prediction Model

In recent years, the market demand for online car-hailing service has expanded dramatically. To satisfy the daily travel needs, it is important to predict the supply and demand of online car-hailing in an accurate manner, and make active scheduling based on the predicted gap between supply and demand. This paper puts forward a novel supply and demand prediction model for online carhailing, which combines the merits of convolutional neural network (CNN) and long short-term memory (LSTM). The proposed model was named convolutional LSTM (C-LSTM). Next, the original data on online car-hailing were processed, and the key features that affect the supply and demand prediction were extracted. After that, the C-LSTM was optimized by the AdaBound algorithm during the training process. Finally, the superiority of the C-LSTM in predicting online car-hailing supply and demand was proved through contrastive experiments.

Design of affinity-aware encoding by embedding graph centrality for graph classification

Deep learning methods for graph classification are critical for graph data mining. Recently, graph convolutional networks (GCNs) have been able to achieve state-of-the-art node classification. A typical process for GCNs includes two iterative steps: node feature encoding and message passing. While the former encodes each graph node independently via the uniform encoding function, the latter updates the features of each node by weighted aggregation of the features of neighboring nodes, where the weights are generated by predefined or learned graph Laplacian. However, their accuracy deteriorates for graph classification tasks because the uniform encoding function encodes all the node features involved. In this study, we propose a novel affinity-aware encoding for graph classification. In our model, we implement a separate encoding function for the neighboring nodes of each node for updating the node features, where the nodes are arranged in the order of affinity values, such as graph centrality, in order to determine the correspondence between an encoding function and a specific neighboring node. Our separate encoding function performs non-Euclidean neighboring encoding for each node by weight sharing, which enables message passing. We also develop two variants based on our separate encoding function: the graph centrality-convolutional neural network (C-CNN) and the graph centrality-graph convolutional network (C-GCN). The former performs the separate encoding function on graph data directly by the function of message passing. The latter combines the separate encoding function with the normalized graph Laplacian implemented on the graph data. Experiments demonstrate that the results obtained by our models are consistent with those obtained by classical convolutional neural networks (CNNs) on the MNIST dataset, and they outperform existing GCNs on the 20NEWS, Reuters8, and Reuters52 datasets. We also apply our two variants to online car-hailing service data for traffic congestion recognition. Our methods show state-of-the-art results compared with GCNs.