Academic researchers, government agencies, industry groups, and individuals have produced forecasts at an unprecedented scale during the COVID-19 pandemic. To leverage these forecasts, the United States Centers for Disease Control and Prevention (CDC) partnered with an academic research lab at the University of Massachusetts Amherst to create the US COVID-19 Forecast Hub. Launched in April 2020, the Forecast Hub is a dataset with point and probabilistic forecasts of incident cases, incident hospitalizations, incident deaths, and cumulative deaths due to COVID-19 at county, state, and national, levels in the United States. Included forecasts represent a variety of modeling approaches, data sources, and assumptions regarding the spread of COVID-19. The goal of this dataset is to establish a standardized and comparable set of short-term forecasts from modeling teams. These data can be used to develop ensemble models, communicate forecasts to the public, create visualizations, compare models, and inform policies regarding COVID-19 mitigation. These open-source data are available via download from GitHub, through an online API, and through R packages.

The primary objective of this paper is to offer a structured and comprehensive list of the barriers associated with implementation of Artificial Intelligence (AI) solutions in Supply Chain Management (SCM). While the broader field of AI has made rapid advances in a relatively short period of time, there are significant barriers that still need to be addressed to harness the true potential of AI. SCM’s dependency on multi-actor collaboration, disparate data sources, unwillingness of actors to embrace AI, change management issues, and lack of AI governance framework poses significant barriers for successful implementation of AI. Drawn from extensive literature review as well as real-world experience, this paper systematically explores and compiles a robust list of barriers of AI implementation in supply chain functions by categorizing them and elaborating their impact at inter- and intra-organizational SCM. Lastly, the paper offers recommendations for practitioners, policymakers, researchers, and governments on how they can work together for AI to be successful.

We developed a novel multiobjective markdown system and deployed it across many merchandising units at Walmart. The objectives of this system are to (1) clear the stores’ excess inventory by a specified date, (2) improve revenue by minimizing the discounts needed to clear shelves, and (3) reduce the substantial cost to relabel merchandise in the stores. The underlying mathematical approach uses techniques such as deep reinforcement learning, simulation, and optimization to determine the optimal (marked-down) price. Starting in 2019, after six months of extensive testing, we implemented the new approach across all Walmart stores in the United States. The result was a high-performance model with a price-adjustment policy tailored to each store. Walmart increased its sell-through rate (i.e., the number of units sold during the markdown period divided by its inventory at the beginning of the markdown) by 21% and reduced its costs by 7%. Benefits that Walmart accrues include demographics-based store personalization, reductions in operating costs with limited numbers of price adjustments, and a dynamic time window for markdowns.

No abstract

No abstract