2nd Workshop on Decision Intelligence and Analytics for Online Marketplaces
August 6, 2023 Long Beach, CA
Keynote speakers are listed in alphabetical order of the last names.
Ruben Lobel
Airbnb
Ruben Lobel is part of the Core Data Science team, leading academic collaborations across the Airbnb marketplace. Previously, he was leading the Emerging Businesses, Marketplace Intelligence and Pricing teams. Before joining Airbnb, Ruben obtained his PhD in Operations Research from MIT and was Assistant Professor of Operations, Information and Decisions at The Wharton School.
Title:
Beyond the simple A/B test: Mitigating interference bias at Airbnb
Abstract:
Airbnb is a two-sided marketplace for stays and experiences. In this talk, I will explore some of the things that make it such a unique platform and some of the challenges running experiments without interference between treatment groups. I will show how Airbnb developed novel cluster experimentation techniques to mitigate the bias in marketplace experiments and measure the magnitude of the bias. I will also discuss more recent research using switchback experiments to mitigate experimental bias in our customer service platform.
Garrett van Ryzin
Amazon
Garrett van Ryzin is a VP/Distinguished Scientist at Amazon in the Supply Chain Optimization Technologies (SCOT) group. Before joining Amazon, he was a Distinguished Scientist and Head of Marketplace Lab at Lyft and Head of Marketplace Optimization Advanced Development at Uber. Garrett was also Paul M. Montrone Professor of Decision Risk and Operations at Columbia University and subsequently Dyson Family Professor of Operations, Technology and Information Management at Cornell Tech. He is an INFORMS and MSOM Fellow and Lanchester Prize recipient. He received a BSEE from Columbia University, and a MS EECS and PhD Operations Research from MIT.
Title:
Market-based capacity management for FBA
Abstract:
Fulfillment by Amazon (FBA) is Amazon’s 3rd party marketplace for e-commerce sellers. In the past decade, FBA has grown rapidly - growth that has only accelerated during the pandemic. By most measures, FBA is now larger than Amazon’s own retail business. This has created a significant challenge for capacity management, since 3rd party sellers have considerable autonomy over how much inventory they send to Amazon. In this talk, we provide an overview of the FBA capacity management problem and describe an innovative market-based mechanism (auction) for capacity recently launched in North America. The auction uses a novel combination of securities and ex-post inspection. It admits a simple bidding strategy, implicitly scores sellers on a combination of sales and profit, and extracts minimal (often zero) revenue from sellers.
Wotao Yin
Alibaba DAMO
Dr. Wotao Yin obtained his PhD in OR from Columbia U. He is the director of the Decision Intelligence Lab of Alibaba U.S. DAMO Academy. Before that, he was a full professor in the Department of Mathematics at UCLA. His research interests include computational optimization and its applications in image processing, machine learning, and other data science problems. He invented fast algorithms for sparse optimization and large-scale distributed optimization. He is been among the top 1% highly-cited mathematicians since 2018. He received an NSF CAREER Award 2006, Sloan Research Award 2007, Morningside Gold Medal 2016, DAMO Award 2021, and Egon Balas Award 2021.
Title:
Green Energy Optimization in Energy Marketplaces
Abstract:
In this talk, we provide insights into microgrid control and pricing within energy marketplaces. Starting with a succinct overview of the electric system, we delve into our energy-optimization strategy from last year's NeurIPS CityLearn Challenge. The presentation concludes with a discussion on our work with a wind energy group to develop their pricing submission strategy, illustrating the key role of pricing decision support.