Article
Engineering, Civil
Maria Vega-Gonzalo, Alvaro Aguilera-Garcia, Juan Gomez, Jose Manuel Vassallo
Summary: The advent of ride-hailing services has caused significant disruptions in the provision of on-demand door-to-door trips within the hailing sector. The introduction of e-hailing, which allows the booking of regulated taxis through digital applications, is a recent development in the sector. This paper focuses on understanding hailing users’ preferences in Spain, considering the controversy after the competition in the hailing market. The study reveals that psychological constructs influence the adoption of ride-hailing and e-hailing, and the frequency of use of hailing services is affected by socio-economic variables, mobility habits, and psychological constructs.
Article
Engineering, Civil
Dun Cao, Kai Zeng, Jin Wang, Pradip Kumar Sharma, Xiaomin Ma, Yonghe Liu, Siyuan Zhou
Summary: In this paper, a BERT-based Deep Spatial-Temporal Network (BDSTN) is proposed to model complex spatial-temporal relations using Points of Interest (POIs) to identify regional functions, showing superior effectiveness and efficiency compared to state-of-the-art methods and other deep learning models in predicting taxi demand.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Construction & Building Technology
Di Wang, Tomio Miwa, Takayuki Morikawa
Summary: This study examines the interrelationships between traditional taxi services and online ridehailing, finding that they have three significant interrelationships: two-way competitive, unilaterally competitive, and complementary. Ridehailing is a formidable competitor for traditional taxis in most cases, but they can also complement each other in certain spatiotemporal circumstances. Therefore, traditional taxis and ridehailing will coexist in the future, and resource allocation is essential for the sustainability of the personal mobility market.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Automation & Control Systems
Zhiyuan Liu, Yang Liu, Cheng Lyu, Jieping Ye
Summary: This article proposes a personalized demand prediction model with two attention blocks to capture spatial and temporal perspectives, achieving superior prediction accuracy for large-scale online taxi-hailing demand.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Engineering, Civil
Dapeng Zhang, Feng Xiao, Gang Kou, Jian Luo, Fan Yang
Summary: Accurate and reliable taxi demand prediction is crucial for intelligent planning and management in the transportation system. Existing studies often overlook the local statistical differences throughout a city's geographical layout, limiting the accuracy improvement of prediction models. In this paper, we propose a new deep learning framework, LC-ST-FCN, that simultaneously learns the spatial-temporal correlations and local statistical differences among regions. Evaluation on a real dataset shows significant improvements compared to baseline models, and visualization results demonstrate the better localization and capture of spatial-related features.
JOURNAL OF ADVANCED TRANSPORTATION
(2023)
Article
Computer Science, Information Systems
Yitong Gan, Hongchao Fan, Wei Jiao, Mengqi Sun
Summary: The traditional taxi industry in China is adapting to the modern trend by incorporating e-hailing applications, leading to changes in driving behaviors for taxi drivers. These changes include increased initiative, more trips during nighttime, and time-saving mobile payment facilities. While e-hailing apps help drivers access more long-distance rides and new pick-up locations, they do not reduce cruising time. Ultimately, these apps improve driver revenue by decreasing unoccupied ratios and increasing operating ratios.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Urban Studies
Pengyu Zhu, Jie Huang, Jiaoe Wang, Yu Liu, Jiarong Li, Mingshu Wang, Wei Qiang
Summary: This study examines taxi demand in Beijing at a 1-kilometer square grid resolution using spatial econometric models. The results show that road network density has the strongest direct and indirect impact on taxi ridership during peak hours. Additionally, there is a relationship between public transportation coverage and taxi ridership, where bus coverage has positive effects and subway coverage has negative effects. The study emphasizes the complex nature of taxi demand and its implications for urban transportation planning.
Article
Engineering, Civil
Neema Davis, Gaurav Raina, Krishna Jagannathan
Summary: The study suggests that using the GraphLSTM model for taxi demand-supply forecasting can achieve competitive performance with lower computational complexity compared to the ConvLSTM model. By representing Voronoi spatial partitions as nodes on a graph, the GraphLSTM model shows competitive performance across different performance metrics.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Di Wang, Tomio Miwa, Takayuki Morikawa
Summary: The study systematically compared the spatial and temporal characteristics of taxi and ride-hailing services in Xiamen, China. While both services share similar spatial patterns in travel demand, taxis show quicker heterogeneity with changes in population density. The balance between taxi industry and ride-hailing services trend oppositely inside and outside Xiamen Island. Additionally, while trip distances have similar statistical properties, the distribution of median trip distances reflects different urban structures.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Economics
Jintao Ke, Xiqun (Michael) Chen, Hai Yang, Sen Li
Summary: This paper proposes an equilibrium model to describe a ride-sourcing market with both ride-pooling (RP) and non-pooling (NP) services considering traffic congestion externality. It suggests that the market can exist in one or multiple equilibria, depending on the fare difference between RP and NP services. The study also reveals a smiling curve relationship between average sojourn time and vehicle fleet size. The research discusses the impacts of labor supply and background traffic on the platform's operating strategy and profit.
TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW
(2022)
Article
Engineering, Industrial
Yuanguang Zhong, Tong Yang, Bin Cao, T. C. E. Cheng
Summary: The study indicates that, under unregulated conditions, on-demand ride-hailing platforms typically have higher prices and profits; the government should encourage competition between on-demand ride-hailing platforms and the traditional taxi industry and adjust regulatory measures based on specific circumstances to maximize overall social welfare and profit.
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS
(2022)
Article
Operations Research & Management Science
S. Srivatsa Srinivas, Rahul R. Marathe
Summary: With the outbreak of COVID-19, the impact on urban transportation has been profound. Researchers have developed a simplified analytical model to investigate the effects of COVID-19 on the pricing and hygiene decisions of e-hailing taxi services. The study explores the potential collaboration between e-hailing taxi firms and original equipment manufacturers to introduce autonomous vehicles for urban transportation during the pandemic. The findings reveal that if the e-hailing taxi firm obtains a significant share from each ride in its collaboration, the hygiene level with autonomous vehicles is always higher, which is crucial for public health.
ANNALS OF OPERATIONS RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Shaojie Qiao, Nan Han, Jiangtao Huang, Yuzhong Peng, Hongguo Cai, Xiao Qin, Zhengyi Lei
Summary: This study proposes a ride-hailing demand prediction algorithm based on multi-agent reinforcement learning, which improves prediction accuracy and response rate, and optimizes ride-hailing dispatching by maximizing the gross merchandise volume (GMV).
APPLIED SOFT COMPUTING
(2023)
Article
Economics
Kentaro Mori, Tomio Miwa, Ryosuke Abe, Takayuki Morikawa
Summary: This study aimed to propose an easily implementable method for forecasting urban transportation demand when autonomous taxi services are adopted. The results showed an increase in the number of trips using taxis, while the usage of other modes is expected to decrease.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2022)
Article
Computer Science, Information Systems
Wenbo Zhang, Chang Xu
Summary: This study investigates app-based taxi movement patterns in large cities using ubiquitous mobile computing techniques. The results show that these services are expanding to more neighborhoods and contributing to an increase in total taxi ridership. Additionally, significant spatial autocorrelations were observed among different services.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Management
Meng Qi, Ying Cao, Zuo-Jun (Max) Shen
Summary: This study introduces a new data-driven distributionally robust framework under a fixed-design setting, proposing a regress-then-robustify method to construct a surrogate empirical distribution of the noise. It addresses the limitations of existing literature that assumes i.i.d. samples and demonstrates the advantages of the proposed approach through numerical experiments.
MANAGEMENT SCIENCE
(2022)
Article
Engineering, Manufacturing
Jie Yang, Fang He, Xi Lin, Max Zuo-Jun Shen
Summary: This paper studies a parking management problem and designs a two-step mechanism to ensure optimal system performance. Numerical examples demonstrate that the mechanism design enhances system performance and robustness.
PRODUCTION AND OPERATIONS MANAGEMENT
(2021)
Article
Transportation Science & Technology
Chengzhang Wang, Xi Lin, Fang He, Max Zuo-jun Shen, Meng Li
Summary: The study investigates a charging system with both fixed and mobile charging services through equilibrium and optimization models; numerical tests demonstrate the algorithm's quick convergence to equilibrium solution and provide managerial insights for hybrid charging system design.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Management
Sheng Liu, Zuo-Jun Max Shen, Xiang Ji
Summary: This study focuses on urban bike lane planning based on fine-grained bike trajectory data. It develops an optimization framework to guide bike lane planning, capturing cyclists' route choices and utility functions. The research demonstrates efficiency of proposed algorithms and quantifies trade-offs between bike trip coverage and lane continuity, highlighting the importance of understanding cyclists' route choices.
M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT
(2022)
Article
Management
Jian Chen, Yong Liang, Hao Shen, Zuo-Jun Max Shen, Mengying Xue
Summary: The study proposes a solution to help omnichannel retailers make offline store location and assortment decisions to maximize profits across online and offline channels. It finds that omnichannel retailers should provide location-dependent offline assortments, the importance of jointly determining offline store locations and assortments, and the necessity of incorporating the online channel in offline-channel planning decisions.
M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT
(2022)
Article
Engineering, Manufacturing
Shaochong Lin, Youhua (Frank) Chen, Yanzhi Li, Zuo-Jun Max Shen
Summary: The study introduces a data-driven risk-averse newsvendor model that utilizes machine learning methods to weigh the similarity between a new product and previous products based on covariates, enabling efficient computation of expected profit and profit risk constraints. The model is proven to be asymptotically optimal.
PRODUCTION AND OPERATIONS MANAGEMENT
(2022)
Article
Management
Hansheng Jiang, Junyu Cao, Zuo-Jun Max Shen
Summary: This study examines the impact of reference effects and consumer heterogeneity on intertemporal pricing and proposes a methodology to estimate heterogeneous consumer reference effects and compute the optimal pricing policy efficiently. The findings emphasize the importance of considering consumer heterogeneity in pricing strategies and suggest that heterogeneous reference effects motivate promotions and price fluctuations.
M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT
(2022)
Article
Engineering, Manufacturing
Long He, Sheng Liu, Zuo-Jun Max Shen
Summary: This study reviews innovative applications and related research areas in urban transport and logistics (UTL), highlighting the sources, types, and uses of data as well as business analytics techniques and software for planning and managing UTL systems. The paper concludes by reflecting on emerging trends and potential research directions in data-driven decision making for smart UTL.
PRODUCTION AND OPERATIONS MANAGEMENT
(2022)
Article
Engineering, Industrial
Jingchuan Chen, Zuo-Jun Max Shen
Summary: This study proposes a fast algorithm for predicting the production process performance in flexible production lines with delayed differentiation under operation control. By formulating practical problems into a mathematical model and offering prediction algorithms, the study verifies the accuracy of these methods and provides a foundation for other transient-based studies.
Article
Management
Zhiyu Zeng, Hengchen Dai, Dennis J. Zhang, Heng Zhang, Renyu Zhang, Zhiwei Xu, Zuo-Jun Max Shen
Summary: Content-sharing social network platforms rely on user-generated content and face limited control over content provision. This study explores the use of social nudges to stimulate content production through social interactions between users. The results show that social nudges immediately increase content supply without affecting quality and also lead to more nudges sent by providers. These effects persist over time and are amplified when there are stronger ties between senders and recipients. The research highlights the value of leveraging co-user influence and provides guidance for incorporating intervention diffusion in social network estimation.
MANAGEMENT SCIENCE
(2023)
Article
Engineering, Industrial
Li Xiao, Zuo-jun Max Shen
Summary: This article examines the impact of providing a carpooling service on customer waiting time and driver utilization in an on-demand service platform. The efficiency of the carpooling service is influenced by the source of customers and the length of a normalized detour. If the carpooling service attracts new customers, both waiting time and driver utilization increase. If the service primarily attracts existing customers, the impact depends on the detour length.
Article
Management
Ziliang Jin, Yulan Wang, Yun Fong Lim, Kai Pan, Zuo-Jun Max Shen
Summary: Shared micromobility vehicles provide an eco-friendly form of short-distance travel within an urban area. To overcome the imbalance between vehicle supply and demand in different service regions, a micromobility operator can use reward incentives and engage a third-party logistics provider (3PL) for vehicle relocation. The study proposes a two-stage stochastic mixed-integer program to optimize vehicle allocation and relocation, and the results show that incorporating rider crowdsourcing and 3PL can increase profit and improve system efficiency.
M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT
(2023)
Article
Robotics
Jingchuan Chen, Zuo-Jun Max Shen
Summary: This article investigates the interactions between manufacturing systems and inventory models, and proposes effective algorithms for analyzing the dynamic behavior of manufacturing systems with regular orders. The approach reduces the state space of the problem and maintains high accuracy.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Engineering, Industrial
Xiaohong Chen, Tianhu Deng, Zuo-Jun Max Shen, Yi Yu
Summary: This article introduces the mission of the Institute of Industrial and Systems Engineers (IISE) and the problems it faces. It identifies three major bottlenecks that limit the industrial implementation of research outcomes and proposes potential solutions, highlighting the importance of data-driven decision methods.
Article
Management
Xiaojing Feng, Ying Rong, Zuo-Jun Max Shen, Lawrence V. Snyder
Summary: When supply disruptions occur, firms need to employ the right pricing strategy. Fixed pricing strategy offers stability but lower profit, while naive pricing strategy brings higher profit. One-period correction strategy results in volatile customer order process and smaller profit. Regression pricing strategy, though advanced, leads to lower profit and greater customer order variability. It is advisable to adjust price to match supply and demand and not eliminate customer order variability completely.
Article
Transportation Science & Technology
Yue Zhao, Liujiang Kang, Huijun Sun, Jianjun Wu, Nsabimana Buhigiro
Summary: This study proposes a 2-population 3-strategy evolutionary game model to address the issue of subway network operation extension. The analysis reveals that the rule of maximum total fitness ensures the priority of evolutionary equilibrium strategies, and proper adjustment minutes can enhance the effectiveness of operation extension.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Hongtao Hu, Jiao Mob, Lu Zhen
Summary: This study investigates the challenges of daily storage yard management in marine container terminals considering delayed transshipment of containers. A mixed-integer linear programming model is proposed to minimize various costs associated with transportation and yard management. The improved Benders decomposition algorithm is applied to solve the problem effectively and efficiently.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Zhandong Xu, Yiyang Peng, Guoyuan Li, Anthony Chen, Xiaobo Liu
Summary: This paper studied the impact of range anxiety among electric vehicle drivers on traffic assignment. Two types of range-constrained traffic assignment problems were defined based on discrete or continuous distributed range anxiety. Models and algorithms were proposed to solve the two types of problems. Experimental results showed the superiority of the proposed algorithm and revealed that drivers with heightened range anxiety may cause severe congestion.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Chuanjia Li, Maosi Geng, Yong Chen, Zeen Cai, Zheng Zhu, Xiqun (Michael) Chen
Summary: Understanding spatial-temporal stochasticity in shared mobility is crucial, and this study introduces the Bi-STTNP prediction model that provides probabilistic predictions and uncertainty estimations for ride-sourcing demand, outperforming conventional deep learning methods. The model captures the multivariate spatial-temporal Gaussian distribution of demand and offers comprehensive uncertainty representations.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Benjamin Coifman, Lizhe Li
Summary: This paper develops a partial trajectory method for aligning views from successive fixed cameras in order to ensure high fidelity with the actual vehicle movements. The method operates on the output of vehicle tracking to provide direct feedback and improve alignment quality. Experimental results show that this method can enhance accuracy and increase the number of vehicles in the dataset.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Mohsen Dastpak, Fausto Errico, Ola Jabali, Federico Malucelli
Summary: This article discusses the problem of an Electric Vehicle (EV) finding the shortest route from an origin to a destination and proposes a problem model that considers the occupancy indicator information of charging stations. A Markov Decision Process formulation is presented to optimize the EV routing and charging policy. A reoptimization algorithm is developed to establish the sequence of charging station visits and charging amounts based on system updates. Results from a comprehensive computational study show that the proposed method significantly reduces waiting times and total trip duration.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)