Research

PhD Research

• “Using Artificial Intelligence to Reduce Food Waste.” with Elena Belavina and Karan Girotra. Major Revision at Management Science. [Document]
  • Finalist, 2024 INFORMS Technology, Innovation Management, and Entrepreneurship Section’s (TIMES) Best Working Paper Competition.
  • 2024 Climate Solutions Fund’s Award Recipient ($111,114).
  • Abstract

    In this study, we estimate the reduction in food waste that arises from the deployment of a system that digitally records instances of food items discarded in a commercial kitchen. We also shed light on the mechanisms that drive this impact. In a quasi-experimental setting, where the system was deployed in about 900 kitchens in a staggered manner, we estimate the impact using synthetic difference-in-differences method. We find that three months after adoption, kitchens generate 29% lower food waste, on average, than they would have in the absence of the system--- without any corresponding reductions in sales. Utilizing a long-short-term-memory fully-convolutional-network classifier, we document that these reductions are accompanied by a 23% decrease in demand chasing, a known bias in human inventory management. Upgrading to a system that uses computer vision to automate waste classification leads to a further 30% reduction in food waste generated by the kitchen a year after the upgrade. This further reduction is due to the accurate recording of infrequent but very high-impact instances of food wasted that employees avoid entering manually. We also observe substantial effect heterogeneity. Smaller kitchens and those with buffet service (vs. table service) experience almost double the reduction in food waste from the adoption of the system and also from the computer vision upgrade.
• “AI Co-Pilots for Data-Driven Perishable Inventory Management.” with Meng Qi, Elena Belavina and Karan Girotra. Draft Available Upon Request.
  • Abstract

    In this study we introduce two AI co-pilots that support perishable inventory management differently. To be more specific, we focus on the periodic review, perishable inventory management problem for perishable goods with a fixed product shelf life. One inventory co-pilot is to provide a data-driven prescriptive solution to the multi-period inventory control problem, directly telling how much a human decision maker should replenish for the upcoming season given past sales data. We justify this prescriptive co-pilot with associated performance guarantees. Building on the data-driven prescriptive copilot, the second copilot is enhanced in terms of detecting potential human decision-making biases in managing perishable inventory. Using machine learning models, it identifies from past user behavior whether a human decision maker is biased in their inventory decision making, and (if so) it also indicates what human bias likely accounts for. Through an online experiment with Prolific workers, we further investigate how human users react to the deployment of different forms of AI assistance and explain why it happens. We find both types of inventory copilots- whether providing data-driven prescriptive solutions or bias detection, enhance perishable inventory management performance for human decision-makers. Additionally, integrating bias detection with prescriptive solutions could foster greater human adherence to algorithmic recommendations.
• “An Experimental Study on Integrating Algorithmic Prescriptions with Human Operators’ Workflows in Commercial Kitchens.” with Meng Qi, Elena Belavina and Karan Girotra. Work in progress.

Undergraduate Research

• “Pricing and Capacity Allocation: Implications for Manufacturers with Product Sharing.” with Bin Dai. Naval Research Logistics 2020, 67(3): 201-222. [Document]

• “Interactions of Traceability and Reliability Optimization in a Competitive Supply Chain with Product Recall.” with Bin Dai, Xia Xie, and Jianbin Li. European Journal of Operational Research 2021, 290(1): 116-131. [Document]