Problem definition: This paper investigates the impact of COVID-19 on e-commerce sales and the underlying operational driver. Academic/practical relevance: As COVID-19 continues to disrupt offline retail, anecdotal evidence suggests a rapid growth of e-commerce. However, the pandemic may also significantly decrease offline logistics capacity, which in turn decreases e-commerce sales. Then, how does e-commerce respond to COVID-19, and what are the corresponding opportunities and challenges? Methodology: We leverage e-commerce sales data from Alibaba and construct a city-day panel across three years, representing sales for all buyers and sellers on the platform across 339 cities in mainland China. We develop three identification strategies to estimate the overall impact of COVID-19 (based on a year-on-year comparison), the impact of COVID-19 intensity (based on the different number of cases across cities), and the impact of corresponding containment measures (leveraging policy changes of checkpoint, partial shutdown, and complete shutdown measures across cities). Results: We provide two key findings. First, across different identification strategies, we observe a common drop and recovery pattern, which illustrates the digital resilience of e-commerce during the pandemic. For example, we estimate an overall decrease of 22% in e-commerce sales during the period of the Wuhan shutdown (January 23–April 7, 2020). However, it recovers in most cities within five weeks. Second, we identify a key operational driver—logistics capacity—that significantly explains the decline and recovery of e-commerce sales during and after the outbreak. Managerial implications: We provide important evidence on how e-commerce responds to and recovers from COVID-19, contrary to the common perception. The evidence in the recovery phase can also inform platforms and policymakers to design digital strategies and invest in logistics infrastructure.

Frequently, policy makers seek to roll out an intervention previously proven effective in a research study, perhaps subject to resource constraints. However, because different subpopulations may respond differently to the same treatment, there is no a priori guarantee that the intervention will be as effective in the targeted population as it was in the study. How then should policy makers target individuals to maximize intervention effectiveness? We propose a novel robust optimization approach that leverages evidence typically available in a published study. Our model can be easily optimized in minutes for realistic instances with off-the-shelf software and is flexible enough to accommodate a variety of resource and fairness constraints. We compare our approach with current practice by proving performance guarantees for both approaches, which emphasize their structural differences. We also prove an intuitive interpretation of our model in terms of regularization, penalizing differences in the demographic distribution between targeted individuals and the study population. Although the precise penalty depends on the choice of uncertainty set, we show that for special cases we can recover classical penalties from the covariate matching literature on causal inference. Finally, using real data from a large teaching hospital, we compare our approach to common practice in the particular context of reducing emergency department utilization by Medicaid patients through case management. We find that our approach can offer significant benefits over common practice, particularly when the heterogeneity in patient response to the treatment is large. This paper was accepted by Chung-Piaw Teo, optimization.

No abstract

No abstract