{"title":"Meal pickup and delivery problem with appointment time and uncertainty in order cancellation","authors":"","doi":"10.1016/j.tre.2024.103845","DOIUrl":"10.1016/j.tre.2024.103845","url":null,"abstract":"<div><div>Online-ordered meal logistics services (OMLSs) that accept online bookings and make vehicle plans to deliver meals from restaurants to customers have recently emerged. Customers have the option to cancel orders that are not delivered by appointment times, leading to significant financial, reputational, and customer losses for the OMLS providers. This study aims to make an appropriate vehicle plan for OMLS providers to minimize the expected total cost under the uncertainty of order cancellations. The problem is formulated as a two-stage stochastic programming model, and sample average approximation equivalent problems are generated using Monte Carlo simulation. To solve the equivalent problems, a parallel adaptive large neighborhood search (pALNS) with statistical guarantees is developed. Experiment results show that the vehicle plan derived from the ALNS is much better than the solution found by Gurobi within 10,800 s, with an average improvement of 14.90%. Additionally, the pALNS provides better statistical bounds in a shorter time compared to both the ALNS and the unsynchronized pALNS. Analytical experiments reveal that earlier cancellations lead to more severe consequences, offering valuable insights for OMLS providers to implement proactive measures to retain “urgent” customers.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The rich get richer: Derivative revenue as a catalyst for bike-sharing subscription services","authors":"","doi":"10.1016/j.tre.2024.103843","DOIUrl":"10.1016/j.tre.2024.103843","url":null,"abstract":"<div><div>By leveraging the derived revenue from subscription services, our study investigates the feasibility of shared bicycle platforms using pricing strategies for these services to enhance their market competitiveness. We establish that, in scenarios where platforms set prices independently, the derived revenue can effectively counterbalance the potential deficits stemming from service expenditures. In a market dominated by exclusive subscription services, an overemphasis on the locking effects can precipitate a mutually detrimental outcome. In a non-exclusive context, the substantial derived revenue can engender a Matthew Effect. Platforms endowed with elevated availability rates are positioned to perpetuate the expansion of their inherent advantages, progressively eroding the market share of their counterparts with diminished availability rates through strategic encroachment. Additionally, we elucidate the strategic dynamics within a competitive platform landscape, underscoring the imperative for platforms to meticulously evaluate their derived revenue scale and devise strategic choices that resonate with their distinctive advantages.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Distributionally robust optimization for pre-disaster facility location problem with 3D printing","authors":"","doi":"10.1016/j.tre.2024.103844","DOIUrl":"10.1016/j.tre.2024.103844","url":null,"abstract":"<div><div>The ongoing advancement of 3D printing technology provides an innovative approach to addressing challenges in disaster relief operations. By utilizing a variety of printing materials, 3D printers can produce essential disaster relief resources needed for disaster relief, effectively satisfying the varied demands that arise after disasters. This paper examines the joint optimization of pre-disaster and post-disaster humanitarian operations. Given the significant unpredictability of natural disasters, we introduce a two-stage distributionally robust optimization model to tackle the uncertainty in the demand for various relief resources. The first stage of the model involves decisions related to pre-disaster facility location, 3D printer deployment, and resource allocation. The second stage model addresses the post-disaster rescue activities, including decisions on the production and transportation decisions of relief resources. To address demand uncertainty, we propose an ambiguity set using the Wasserstein metric and reformulate the two-stage distributionally robust optimization model into a tractable formulation. To solve this problem, we employ a Benders decomposition algorithm with an acceleration strategy. The performance of our proposed model and algorithm is evaluated via a real-world case. Numerical experiments reveal that our distributionally robust optimization model outperforms the benchmark model across various metrics. Additionally, we conduct a series of effect analyses and provide managerial insights for decision-makers involved in disaster relief operations.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Traffic Flow Outlier Detection for Smart Mobility Using Gaussian Process Regression Assisted Stochastic Differential Equations","authors":"","doi":"10.1016/j.tre.2024.103840","DOIUrl":"10.1016/j.tre.2024.103840","url":null,"abstract":"<div><div>Current methods for detecting outliers in traffic streaming data often struggle to capture real-time dynamic changes in traffic conditions and differentiate between genuine changes and anomalies. This study proposes a novel approach to outlier detection in traffic streaming data that effectively addresses stochasticity and uncertainty in observations. The proposed method utilizes Stochastic Differential Equations (SDEs) and Gaussian Process Regression (GPR). By employing SDEs, we can capture drift and diffusion estimates in traffic streaming data, providing a more comprehensive modeling of the data generation process. Integrating GPR allows precise Bayesian posterior inferences for outlier detection within the SDE framework. To improve practicality, we introduce a flexible threshold-setting mechanism using statistical testing to control the false positive rate. This adaptability helps strike a balance between model fitting and complexity in outlier detection. Compared to traditional SDE-based methods, our SDE-GPR outlier detection method demonstrates enhanced robustness and better adaptability to the complexities of traffic systems. This is evidenced through an empirical study using time series data collected in California, USA. Overall, this study introduces a more advanced and accurate approach to outlier detection in traffic streaming data, paving the way for improved real-time traffic condition monitoring and management.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prototype augmentation-based spatiotemporal anomaly detection in smart mobility systems","authors":"","doi":"10.1016/j.tre.2024.103815","DOIUrl":"10.1016/j.tre.2024.103815","url":null,"abstract":"<div><div>In complex mobility systems, the widespread presence of spatiotemporal anomaly patterns poses substantial challenges to effective governance and decision-making. A notable example of this challenge is evident in traffic anomalous incidents detection, where the combination of low accuracy in anomaly detection and poor scenario generalization performance significantly impacts the overall performance of anomaly detection. This paper introduces a prototype augmentation-based framework tailored for spatiotemporal anomaly detection in the context of smart mobility system. This framework utilizes prototype augmentation technique to enhance the diversity of anomaly patterns, ensuring that the integrity of the original anomaly information is preserved. Essentially, the prototype augmentation-based anomaly detector employed in this framework is a hybrid unsupervised-supervised stacking ensemble. It leverages the strengths of unsupervised component learners to generate pseudo dimensions while integrating a supervised meta-detector for evaluating the component learners’ performance across diverse environmental contexts. Additionally, we materialize this framework and assess its performance in detecting anomalous line-pressing incidents. Empirical results demonstrate our framework’s superior accuracy and transferability in detecting anomalous traffic incidents compared to alternative methods using a real-world dataset.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Personalized origin–destination travel time estimation with active adversarial inverse reinforcement learning and Transformer","authors":"","doi":"10.1016/j.tre.2024.103839","DOIUrl":"10.1016/j.tre.2024.103839","url":null,"abstract":"<div><div>Travel time estimation is important for instant delivery, vehicle routing, and ride-hailing. Most studies estimate the travel time of specified routes, and only a few studies pay attention to origin–destination travel time estimation (OD-TTE) without a specified route. Moreover, most of these studies on OD-TTE ignore the personalized route preference and the cost of data annotation. To fill this research gap, we analyze the individual route preference and propose a personalized origin–destination travel time estimation method based on active adversarial inverse reinforcement learning (AA-IRL) and Transformer. To analyze the personalized route preference, we integrate adversarial inverse reinforcement learning with active learning, which effectively reduces the cost of sample annotation. After inferring the possible routes, we propose AdaBoost multi-fusion graph convolutional Transformer network (AMGC-Transformer) for travel time estimation. Numerical experiments conducted on ride-hailing and online food delivery trajectories in China validate the advantage of our method. Compared to relevant studies, our approach can improve F1-score of route inference by 2.50–3.35% and reduce the mean absolute error of OD-TTE by 7.44–11.66%.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dynamic matching radius decision model for on-demand ride services: A deep multi-task learning approach","authors":"","doi":"10.1016/j.tre.2024.103822","DOIUrl":"10.1016/j.tre.2024.103822","url":null,"abstract":"<div><div>As ride-hailing services have experienced significant growth, most research has concentrated on the dispatching mode, where drivers must accept the platform’s assigned trip requests. However, the broadcasting mode, in which drivers can freely choose their preferred orders from those broadcast by the platform, has received less attention. One crucial but challenging task in such a system is the determination of the matching radius, which usually varies across space, time, and real-time supply/demand characteristics. This study develops a <strong>D</strong>eep <strong>L</strong>earning-based <strong>M</strong>atching <strong>R</strong>adius <strong>D</strong>ecision (DL-MRD) model that predicts key system performance metrics for a range of matching radii, which enables the ride-hailing platform to select an optimal matching radius that maximizes overall system performance according to real-time supply and demand information. To simultaneously maximize multiple system performance metrics for matching radius determination, we devise a novel multi-task learning algorithm named <strong>W</strong>eighted <strong>E</strong>xponential <strong>S</strong>moothing <strong>M</strong>ulti-task (WESM) learning strategy that enhances convergence speed of each task (corresponding to the optimization of one metric) and delivers more accurate overall predictions. We evaluate our methods in a simulation environment designed for broadcasting-mode-based ride-hailing service. Our findings reveal that dynamically adjusting matching radii based on our proposed approach significantly improves system performance.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stockyard allocation in dry bulk ports considering resource consumption reduction of spraying operations","authors":"","doi":"10.1016/j.tre.2024.103816","DOIUrl":"10.1016/j.tre.2024.103816","url":null,"abstract":"<div><div>Stockyard allocation is a crucial segment of operational decision-making in dry bulk ports (DBPs). The stockyard allocation plan determines the storage position and duration of each stockpile to avoid operational delays in stockyards. Spraying operations, a unique operation in DBPs, are significantly influenced by stockyard allocation plans. Port operators regularly conduct spraying operations to prevent dust diffusion during the storage of dry bulk materials in stockyards. The spraying operation system consumes substantial electrical energy to transport the water to the designated material pile and spray large amounts of water onto its surface. Due to the layout constraints of pipelines and spraying nozzles, different stockyard allocation plans lead the varying consumptions of electrical energy and water resources for spraying operations. However, previous studies on the stockyard allocation problem frequently ignore the impacts of the stockyard allocation plan on the resource consumption of spraying operations. To fill this gap, this paper proposes a stockyard allocation model that uniquely considers the resource consumption of spraying operations to balance operation efficiency and resource consumption in stockyards from a global perspective. With the goal of minimizing the total cost, including operation delay penalties in stockyards and the electricity and water costs of spraying operations, a series of comprehensive experiments was conducted based on practical data collected from a major DBP in China under varying stockpile densities and stockyard efficiency properties. The results clearly show significant differences in the stockyard allocation plan and the total cost resulting from considering and disregarding the resource consumption of spraying operations in the stockyard allocation decision-making process. With only a 3.09% increase in average delay time in stockyards, the proposed model can reduce the total cost by 19.26%, the electricity cost by 54.06% and the water cost reduction by 35.09%. Meanwhile, the carbon emissions are reduced 75 tons on average for spraying operations and the Whale Optimization Algorithm (WOA) performs well on large-scale instances. The proposed model can avoid unnecessary resource consumption of spraying operations with acceptable operation delay penalties in stockyards.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Inhibitors in ridesharing firms from developing Nations: A novel Integrated MCDM – Text Mining approach using Large-Scale data","authors":"","doi":"10.1016/j.tre.2024.103832","DOIUrl":"10.1016/j.tre.2024.103832","url":null,"abstract":"<div><div>Our study identifies major impediments (or inhibitors) faced by Transportation Network Companies (TNCs) such as Uber, Lyft, and Ola within the context of developing nations. While existing studies on TNCs centered on passenger adoption and drivers’ perspectives, we quantitively assess the inhibitors and provide mitigation strategies. To achieve this, we use machine learning methods, particularly Latent Dirichlet Allocation (LDA) and emotion analysis on large-scale public data, to understand and classify consumer perspectives on TNCs into multiple themes. The latent theme helps experts of different ridesharing firms get a holistic perspective of riders on TNCs, assisting them in identifying the inhibitors. Using the Delphi method, we were able to achieve a consensus in identifying six primary and nineteen secondary inhibitors. We rank the primary inhibitors based on the optimal weight obtained using the Bayesian Best Worst Method. To minimize uncertainty and imprecise judgment in decision-making, we combine the grey theory with the Decision-Making Trial and Evaluation Laboratory (Grey-DEMATEL) to identify the interrelationships among the secondary inhibitors. Moreover, we perform sensitivity analysis to show the robustness of our solution. Contrary to conventional perception, our findings indicate that the government is the primary inhibitor for TNCs due to current policy and discrepancies in regulations between central and states. Additionally, our studies introduce five new inhibitors to the literature, which include drivers inciting trip cancellation to avoid commission, internal coalition of drivers, commission miscomprehension among drivers, limited infrastructure for cashless operation, and internal conflict and dysfunction within the department. The findings from large-scale data analysis, coupled with group decision-making, offer various managerial implications that can guide future managers and policymakers to enhance the operational efficiency of firms.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Socially responsible e-commerce supply chains: Sales mode preference and store brand introduction","authors":"","doi":"10.1016/j.tre.2024.103829","DOIUrl":"10.1016/j.tre.2024.103829","url":null,"abstract":"<div><div>Motivated by the widespread adoption of corporate social responsibility (CSR), we investigate a socially responsible e-commerce supply chain where the E-platform owns a store brand product and supports online sales of the manufacturer’s product under agency selling or reselling. The socially responsible firm has a mixed objective of its profit and consumer surplus. We explore how the firms’ CSR concern affects their decisions and economic performance. Our results contradict conventional wisdom which suggests that a firm has to sacrifice profitability to achieve social responsibility and that a firm’s CSR concern benefits its supply chain partner. Instead, we show that under agency selling, the E-platform’s concern on consumers can improve its own profit while harming the manufacturer’s profit. Furthermore, when both firms are socially responsible, their consumer concern can improve their profits simultaneously under reselling, leading to a “doing well by doing good” effect. As horizontal or vertical differentiation between the two products increases, this effect is more likely to be realized. Regarding firms’ sales mode preferences, in a traditional for-profit supply chain, agency selling is the only mode preferred by both parties. However, in a socially responsible supply chain, they can achieve preference alignment under either agency selling or reselling.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":null,"pages":null},"PeriodicalIF":8.3,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}