Search

This paper considers how an online food delivery platform can improve last-mile delivery services' performance using multi-source data. The delivery time is one critical but uncertain factor for online platforms that also regarded as the main challenges in order assignment and routing service. To tackle this challenge, we propose a data-driven optimization approach that combines machine learning techniques with capacitated vehicle routing optimization. Machine learning methods can provide more accurate predictions and have received increasing attention in the operations research field. However, different from the traditional predict-then-optimize paradigm, we use a new smart predict-then-optimize framework, whose prediction objective is constructed by decision error instead of prediction error when implementing machine learning. Using this type of prediction, we can obtain a more accurate decision in the following optimization step. Efficient mini-batching gradient and heuristic algorithms are designed to solve the joint order assignment and routing problem of last-mile delivery service. Besides, this paper considers the mutual effect between routing decision and delivery time, and provides the corresponding solution algorithm. In addition, this paper conducts a computational study and finds that the proposed method's performance has an approximate 5% improvement compared with other methods. [ABSTRACT FROM AUTHOR]

Vaccine passport is recognized as a necessary policy to revive the economy during the outbreak of epidemic with asymptomatic infection, and has been widely adopted in the global world. But implementing vaccine passport inevitably increases the infection risk when the vaccine efficacy is not perfect. Choosing a suitable level of vaccine passport with the consideration of vaccine imperfection is extremely important, which is less studied in the existing literature. In this paper, a novel epidemic model is proposed to consider the mixed impacts of vaccination, including vaccination coverage, vaccine efficacy, and vaccine passport, and the heterogeneous mean-filed (HMF) method is used to analyze the model. Both analytical and numerical results indicate that the introduction of vaccine passport will largely weaken the effect of vaccination and decrease the epidemic threshold in either homogeneous or heterogeneous network structure. Especially, when the efficacy of vaccine is lower than a certain value, if vaccine passport is implemented, increasing vaccination coverage may instead increase the number of infections. The results suggest that the proper vaccination-related combinations are: medium/high vaccination coverage, high vaccine efficacy, and low/medium vaccine passport. In addition, the upper bounds of vaccine passport under different combinations of vaccination coverage and vaccine efficacy are explored based on the epidemic threshold. [ABSTRACT FROM AUTHOR]

The aim of the study is to investigate the effect of policy incentives on residents' willingness to use community health centres for initial diagnosis. A cross-sectional survey with specific multiple price-list experiments was conducted in Guizhou, China. We were able to use in-depth individual interviews with a total of 422 participants. Our results showed that both financial and non-financial policy incentives can facilitate the utilisation of the community health centres. Approximately 60% of the respondents reported an increase in their willingness to use community health centres after the presentation of the financial policy, whereas 50% of respondents expressed an increase in their willingness to use community health centres with the non-financial policy. However, to some specific subgroups, such as residents with low trust, residents without chronic disease, residents with less healthcare visits and risk-averters, the impact of policy incentives were limited. The policy incentives are useful tools to attract more visitors to community health centres for initial diagnosis; however, their incentive effects vary in different subgroups. Thus, to change patients' perceptions regarding healthcare provider choice for initial diagnosis, policymakers should consider the heterogeneous responses of patients to policy incentives and focus their efforts on key cohorts. Policies incentives have been initiated to encourage the use of community health centres for initial diagnosis, but it is unclear how the effects of those policies are for certain patients. Both financial and non-financial policy incentives are useful tools to attract more visitors to community health centres for initial diagnosis; however, their incentive effects vary in different subgroups. Policymakers should consider the heterogeneous responses of patients to policy incentives and focus their efforts on key cohorts. [ABSTRACT FROM AUTHOR]