Online Ride-hailing Research Articles

Unlocking Hidden Demand: Utilizing Computer Vision for Street-Hailing Optimization in a Taxi Company in Jakarta

Despite the technology disruption from online ride-hailing, street-hailing is still popular among certain people in Jakarta, the capital city of Indonesia. However, the traditional street-hailing faces several challenges for the taxi operators. Unlike ride-hailing apps where customers and drivers are matched and recorded digitally, street-hailing often lack visibility into street demand that is not always successfully picked up, which can lead to inefficiencies in fleet utilization, highlighting a significant operational gap between traditional taxi services and modern ride-hailing platforms. Artificial Intelligence (AI) and Computer vision (CV) technologies offer a transformational approach to improve visibility and identify the unmet demand for street-hailing within urban transportation in Jakarta. Prior to its implementation, it is important to assess the potential business impact from deploying this digital innovation. This research highlights inference statistics combined with qualitative analysis to evaluate the potential demand that can be captured through CV systems. By leveraging historical taxi trajectory data and interviewing drivers and customers, we aim to uncover patterns and estimate unmet demand to ensure the system development will impact the taxi business and improve the service efficiency and customer satisfaction. This preliminary analysis serves as a foundation for strategic planning of CV system for street-hailing detection implementation.

Forecasting urban passenger transportation emissions: a green and new energy approach

ABSTRACT Passenger transportation significantly contributes to urban carbon dioxide emission. Decreasing these emissions is essential to achieving low-carbon development. This research focused on Xi’an City to enhance previous research works by considering factors such as road greening, online ride-hailing, and use of vehicles with new energy sources. Using system dynamics method, a carbon dioxide emission prediction model was developed for urban passenger transportation in Xi’an. The developed model estimated total emissions from 2012 to 2021 and projected carbon dioxide emission reduction plans through six different scenarios for the time period of 2023 to 2032. The analysis identified private cars as the main contributors to carbon emission in urban passenger transportation. Single scenario simulations indicated that passenger traffic in Xi’an would not achieve carbon emission peak by 2030, but multi-scenario simulations showed it would. Specific recommendations for carbon emission reduction in urban passenger transportation were provided, focusing on travel patterns, energy sources, and promotion of green initiatives.

Analysis and Solution of the Governance Dilemma of Infringement of Car-Hailing Platforms under Sharing Economy

In the current era of rapid development of the Internet, the sharing economy based on the Internet, which combines individual idle resources through the "P2P" mode with the demand side, has emerged at the historic moment and caused various commercial activities. As the leading industry in the sharing economy, online ride-hailing not only mobilizes the social transport capacity and maximizes the economic dividend, but also causes many legal problems due to the lag of laws and regulations. This paper takes the basic legal relationship of online ride-hailing as the starting point, analyzes the infringement disputes arising in the supervision, and puts forward some suggestions for improving online ride-hailing from the relief system and the distribution of legal responsibilities.

Responsible Bandit Learning via Privacy-Protected Mean-Volatility Utility

For ensuring the safety of users by protecting the privacy, the traditional privacy-preserving bandit algorithm aiming to maximize the mean reward has been widely studied in scenarios such as online ride-hailing, advertising recommendations, and personalized healthcare. However, classical bandit learning is irresponsible in such practical applications as they fail to account for risks in online decision-making and ignore external system information. This paper firstly proposes privacy protected mean-volatility utility as the objective of bandit learning and proves its responsibility, because it aims at achieving the maximum probability of utility by considering the risk. Theoretically, our proposed responsible bandit learning is expected to achieve the fastest convergence rate among current bandit algorithms and generates more statistical power than classical normality-based test. Finally, simulation studies provide supporting evidence for the theoretical results and demonstrate stronger performance when using stricter privacy budgets.

A Reinforcement Learning and Prediction-Based Lookahead Policy for Vehicle Repositioning in Online Ride-Hailing Systems

A Reinforcement Learning and Prediction-Based Lookahead Policy for Vehicle Repositioning in Online Ride-Hailing Systems

A District-Centric Attention Mechanism Approach for Online Ride-Hailing Demand Forecasting

A District-Centric Attention Mechanism Approach for Online Ride-Hailing Demand Forecasting

Online Ride-hailing Demand Prediction Model Based on GRU & LSTM

While online car-hailing provides fast and convenient services, it has the same problems in the process of ‘seeking customers’ as traditional taxis. With the research goal of the demand for online ride-hailing, an online ride-hailing demand forecast model based on G & LSTM is proposed. Firstly, grey relational degree analysis and other methods are used to analyze which and how the relevant factors affect the demand for online car-hailing. Secondly, the demand prediction model of online car-hailing based on GRU&LSTM is trained an adjusted. Through the adjustment and comparison experiment, the values of each parameter in the model are properly adjusted. Finally, based on the running data of Chengdu, the model proposed is verified and evaluated. The experimental results show that the GRU&LSTM prediction model has good prediction effect. By comparing the prediction effect of weighting data and unweighting data, it can be seen that weighted data has better prediction effect.

A prediction-based iterative Kuhn-Munkres approach for service vehicle reallocation in ride-hailing

ABSTRACT Online ride-hailing services provide additional transportation capability by recruiting private vehicles to meet people’s growing travel demand. To ensure the profitability of drivers and platforms, pick-up efficiency and frequency must be maintained at high levels. Therefore, consistency between the spatial distribution of drivers and that of travel demand becomes a key issue to address. This paper proposes a prediction-based iterative Kuhn-Munkres approach for service vehicle reallocation in the context of large-scale online ride-hailing. Firstly, preliminaries are formally defined and a novel mathematical model for the problem is proposed. Secondly, a deep spatio-temporal residual perception network is designed to accurately predict travel demand. Thirdly, an iterative Kuhn-Munkres approach combined with an improved A-Star algorithm is developed to reallocate service vehicles to spatial locations according to their distinct travel demand densities. Finally, extensive experiments are conducted to evaluate and verify the performance of the proposed approach.

Optimal pricing strategy of an on-demand platform with cross-regional passengers

Recent years have witnessed the emergence and prosperity of online ride-hailing, which empowers the traditional taxi industry with information technology. However, the ride-hailing platform has no direct control over drivers, one of the biggest challenges for the platform is how to balance the supply and the demand. Considering the cross-regional demand and the surge demand, this paper focuses on the pricing strategy of the ride-hailing platform, and further introduces strategies such as bonus incentive and information sharing. We find that when facing demand surging and supply shortage in one region, the platform can adopt surge pricing or bonus incentive in the adjacent region before the demand surges to balance the supply and the demand. Specially, the surge pricing strategy benefits the platform when the surge demand is high or the cross-regional demand is low, but the bonus incentive strategy has the opposite effect. The existence of cross-regional demand improves the performance of the bonus incentive strategy but reduces that of the surge pricing strategy. We further show that the platform prefers bonus incentive to surge pricing when only a small number of drivers are required to move. But bonus incentive always improves social welfare better than surge pricing. Extending to information asymmetry, information sharing can also encourage more drivers to move. However, the effect is limited such that the proportion of drivers who move will not exceed a threshold. The platform also has the incentive to share false information, which makes drivers question the credibility of the shared information. In this case, the surge pricing strategy can be used as a costly signal to verify the credibility of the information.

The Determination of Legal Liability in the Infringement of Online Ride-Hailing Service

In recent years, with the gradual rise of "Internet +", the sharing economy based on the Internet is flourishing and the online ride-hailing service is a typical and representative product under this background. Online ride-hailing services are apps that connect passengers and local drivers using their personal vehicles. There are numerous companies in China performing online ride-hailing platforms, and the main examples are Didi, Caocao, T3, Shouyue and Meituan. A mature industry though it is, there are still some controversies about the responsibility of traffic accidents involving hailed cars. As an intermediary providing ride-hailing service, whether and how the ride-hailing platform should be held responsible in traffic accidents involving the hailed cars is of great concern. In this paper, the authors divide the various forms of online ride-hailing services into different cases based on the relationship between drivers, passengers and platforms. Based on this classification, the authors discuss the legal responsibility in the tort of online ride-hailing services.

Will the Order Be Canceled? Order Cancellation Probability Prediction Based on Deep Residual Model

Online ride-hailing is gradually becoming one of the indispensable travel modes for people. Online ride-hailing platforms receive tens of thousands of taxi travel orders every day. However, some orders are canceled by the user after the driver answers. User cancellation of orders will disrupt the regular operation of the taxi platform, reduce the efficiency and income of drivers on the online ride-hailing platform, and affect the ride experience of other users. To capture the relationship between the cancellation probability of online taxi orders and users, we first analyze the factors that affect users’ cancellation of online taxi orders. We find that the cancellation probability of online ride-hailing orders is highly correlated with the travel time of the online taxi, the distance between vehicle and passengers, road congestion conditions, and alternative transportation resources around the passengers. Second, a deep residual network-based ride-hailing order cancellation probability prediction model (DeepOCP) is designed to predict the probability of a user canceling an answered online-hailing order. Finally, the Didi Chengdu Express public data set is used to test the model’s effectiveness. This paper is the first study to use a deep-learning model to predict the cancellation probability of online ride-hailing orders.

Benefits of Electric Motorcycle in Improving Personal Sustainable Economy: A View from Indonesia Online Ride-Hailing Rider

The energy cost of electric vehicles is reportedly less than its internal combustion engine counterpart due to using technologies to boost efficiency through regenerative braking. Based on this condition, a possibility of its implementation as veh

PSafety: Privacy-Preserving Safety Monitoring in Online Ride Hailing Services

Online Ride Hailing (ORH) services gain remarkable development in the past decade, which enable riders and drivers to establish optimized rides via mobile device. To guarantee user safety, ORH service providers often monitor the ride trajectory and report the abnormal behavior once a trajectory deviation occurs. Along with the advantage of safety monitoring raises some vital privacy concerns on user location information leakage. In this paper, we propose a privacy-preserving safety monitoring scheme for ORH services, called pSafety. It enables an ORH service provider to detect user’s trajectory deviation without learning anything about users’ locations. In pSafety, we propose two secure trajectory similarity computation algorithms by using somewhat homomorphic encryption, which are used to plan an agreed path and measure trajectory deviation, respectively. Furthermore, we also design a ciphertext compression algorithm and a secure comparison protocol to improve efficiency. Theoretical analysis and experimental evaluations show that pSafety is secure, accurate and efficient.

Analyze factors influencing drivers' cell phone online ride-hailing software using while driving: a case study in China

Analyze factors influencing drivers' cell phone online ride-hailing software using while driving: a case study in China

Policy Evaluation and Policy Style Analysis of Ride-Hailing in China from the Perspective of Policy Instruments: The Introduction of a TOE Three-Dimensional Framework

Online ride-hailing in China brings convenience for the public, but it has caused several problems, such as inadequate supervision, data security risks, and financial risks. This new industry has also disrupted the traditional taxi market. China’s government implemented some policies, which were initially disorderly tightening, and then formed the policy system responding to various needs for tackling these issues gradually. There were some policy fluctuations and regulatory effects during this period, therefore, it is imminent to evaluate the online ride-hailing policy text. In this paper, we took 43 online ride-hailing policies as samples, with the consideration of policy instruments and statistical inspection methods. In this paper, we also constructed an innovative three-dimensional analysis framework by combining content analysis, and further identify the ride-hailing policy development during different stages of development periods (2016–2022). Digging into the problems existing in the new online ride-hailing, policies were drawn by module division, unit coding, inductive statistics, the quantitative evaluation of policy text content, and TOE (technology-organization-environment) style analysis. Finally, we provide insightful policy recommendations for online ride-hailing policies, committed to providing theoretical support and a decision-making basis for governance policies in the transportation industry.

Discovering Implicit Working Pace of Online Ride-Hailing Drivers: An Exploratory Study

Due to convenience and flexibility, online ride-hailing has become increasingly more prevalent across the world. However, many violations and road crashes involving online ride-hailing were related to the unhealthy working pace of drivers, especially inadequate rest. This paper enriches the literature by providing a first look into the latent break patterns of online ride-hailing drivers based on a one-month order record dataset. A data mining and knowledge discovery process is presented for extracting and analyzing characteristics of online ride-hailing drivers’ work and rest based on GPS trajectory data, as follows: 1) logical judging to identify non-work order-gaps; 2) dynamic topic modeling to discover latent break patterns; and 3) integrating the topic modeling results with feature analysis results of order-gaps to summarize the time-dependent characteristics of online ride-hailing drivers’ special working pace. The case study results show that the latent break patterns extracted from two cities’ online ride-hailing order records are significantly different in the strength and cycles of the topics, which is greatly related to the travel supply-demand conditions and urban characters. Furthermore, the proposed analytical framework can help mobile transportation platform companies to better understand online ride-hailing markets from the perspective of drivers and to adjust their marketing strategies in real time.

Interrelationships between traditional taxi services and online ride-hailing: empirical evidence from Xiamen, China

• The study establishes a bivariate Tobit model to examine the interrelationships between traditional taxis and ride-hailing using real-field data. • Parameter estimates suggest that both competitive and complementary relationships exist between traditional taxis and ride-hailing. • Relationships between travel demands and built-environment factors are revealed. • Suggestions are given for the sustainability of the personal mobility market. This study aimed to examine the underlying interrelationships between traditional taxi services and online ride-hailing. To this end, demand data for these two mobility modes were collected from Xiamen Island, China, for three typical days in June 2020. By considering censoring and the potential interdependence and endogeneity of the demand variables, a bivariate Tobit model was established. Through parameter estimation with real-field datasets, the conjecture about the interdependence was verified, and three types of significant interrelationships were identified: two-way competitive, unilaterally competitive and complementary. Under most spatiotemporal circumstances, ride-hailing acts as a formidable competitor for traditional taxis, whereas the latter only demonstrate significant competitiveness in half of the cases. It is noteworthy that the western residential area of Xiamen Island is found to be a blue ocean during the early morning, in which these two parties are complementary to serve an unsaturated market. From empirical analyses, it is concluded that traditional taxis will co-exist with ride-hailing for the foreseeable future, and reasonable resource allocation is needed on both sides for the sustainability of the personal mobility market. The methodology and findings should provide valuable insights for practitioners and decision-makers in framing strategies and regulations towards sustainable urban mobility.

Does Online Ride-Hailing Service Improve the Efficiency of Taxi Market? Evidence from Shanghai

Online ride-hailing services, which are characterized by online matching, are generally considered improving the work efficiency of taxi drivers and bring disruptive changes to the taxi market. We use the historical and contemporaneous trip-level big data of Shanghai online ride-hailing drivers and traditional cruising taxi drivers, structure the data into shift and hour levels, and compare the two types in terms of efficiency. The comparison results indicate that the overall capacity utilization rate of online ride-hailing drivers is slightly higher than that of cruising taxi drivers, but it is mainly driven by part-time drivers. We confirm the role of flexible work and market scale in improving capacity utilization, but do not find the impact of online matching mechanisms. From the perspective of the drivers’ work efficiency, the similar capacity utilization of the two types of full-time workers is consistent with Cramer and Krueger’s (2016) evidence in New York. Online matching and street searching achieve almost equal efficiency in densely populated urban areas. However, from the perspective of supply and demand matching, online ride-hailing creates a more flexible supply and is more adaptable to the changes in demand, which improves the overall taxi market efficiency.

Multigraph Aggregation Spatiotemporal Graph Convolution Network for Ride-Hailing Pick-Up Region Prediction

The prediction of pick-up regions for online ride-hailing can reduce the number of vacant vehicles on the streets, which will optimize the transportation efficiency of cities, reduce energy consumption and carbon emissions, and increase the income of online ride-hailing drivers. However, traditional studies have ignored the temporal and spatial dependencies among pick-up regions and the effects of similarity of POI attributes in different regions in modelling, making the features of the model incomplete. To address the above problems, we propose a new multigraph aggregation spatiotemporal graph convolutional network (MAST-GCN) model to predict pick-up regions for online ride-hailing. In this paper, we propose a graph aggregation method to extract the spatiotemporal aspects and preference features of spatial graphs, order graphs, and POI graphs. GCN is used on the aggregated graphs to extract spatial dimensional features from graph-structured data. The historical data are sequentially divided into temporal granularity according to the period, and convolution operations are performed on the time axis to obtain the features in the temporal dimension. The attention mechanism is used to assign different weights to features with strong periodicity and strong correlation, which effectively solves the pick-up region prediction problem. We implemented the MAST-GCN model based on the PyTorch framework, stacked with a two-layer spatiotemporal graph convolution module, where the dimension of the graph convolution is 64. We evaluate the proposed model on two real-world large scale ride-hailing datasets. The results show that our method provides significant improvements over state-of-the-art baselines.

Joint prediction of zone-based and OD-based passenger demands with a novel generative adversarial network

Online ride-hailing plays an important role in modern urban transportation systems, and accurate short-term passenger demand prediction contributes to improving ride-hailing services. Many existing studies have made great achievements in zone-based demand prediction. However, origin–destination (OD)-based demand prediction has attracted little attention, even though it provides abundant information and is of high practical importance, e.g., it facilitates the routing and matching of ride-hailing services. Considering the importance of both types of demands, a conditional generative adversarial network (CGAN) with Wasserstein divergence (CWGAN-div) is proposed to jointly predict zone-based and OD-based demands. Residual blocks are utilized to capture internal spatiotemporal features, which benefit the training and prediction processes of the CWGAN-div model. Conditional information is also incorporated to characterize the external dependencies of the demands. Numerical experiments are performed by using GPS trajectory data from Didi Chuxing, Chengdu, China. The results show that the proposed CWGAN-div model yields good joint prediction performance and outperforms both classic models (historical average (HA) and convolutional neural network (CNN) models) and other prevailing GAN models (i.e., GAN, CGAN, Wasserstein GAN with a gradient penalty (WGAN-GP), and GAN with Wasserstein divergence (WGAN-div)). The proposed CWGAN-div model displays promise for the joint prediction of zone-based and OD-based passenger demands.