Speaker: Joline Uichanco, Ross School of Business, University of
\nMichigan<\/p>\n
Date & Time: April 25, 2023, Tuesday 12:30<\/p>\n
Place: EA-409<\/p>\n
Title: Overcoming the profitability problem of e-commerce retail using
\ndata-driven product framing<\/p>\n
Abstract: E-commerce retail is known to suffer from thin profit margins.
\nUsing the data from a major U.S. retailer, we show that jointly planning
\nproduct framing and order fulfillment can have a significant impact on
\nonline retailers’ profitability. We study a joint product framing and
\norder fulfillment problem. In each period, the retailer needs to decide
\nhow to “frame” (i.e., display, rank, price) each product on her website
\nas well as how to fulfill a new demand. We use techniques such as
\nrandomized algorithms and graph-based algorithms to provide a tractable
\nsolution heuristic. Our proposed policy significantly reduces shipping
\ncosts by using product framing to manage demand so that it occurs close
\nto the location of the inventory.<\/p>\n
Bio: Joline Uichanco is an Associate Professor of Technology &
\nOperations in the Ross School of Business at the University of Michigan,
\nwhere she has been a faculty member since 2014. Her primary research
\narea is on data-driven decision-making for applications such as
\nscheduling, inventory management, pricing, and humanitarian logistics.
\nDr. Uichanco has collaborated actively with several industry or
\ngovernment partners such as Target, National Grid, Best Buy, and the
\nPhilippine government. She recently served as a Senior Research
\nScientist at Amazon. Dr. Uichanco holds a Ph.D. in Operations Research
\nfrom the Massachusetts Institute of Technology (MIT).<\/p>\n","protected":false},"excerpt":{"rendered":"
Speaker: Joline Uichanco, Ross School of Business, University of Michigan Date & Time: April 25, 2023, Tuesday 12:30 Place: EA-409 Title: Overcoming the profitability problem of e-commerce retail using data-driven product framing Abstract: E-commerce retail is known to suffer from thin profit margins. Using the data from a major U.S. [\u2026] <\/p>\n