We are delighted to welcome Professor Mathieu Dahan,Georgia Institute of Technology, to host a research seminar discussing ‘Prescriptive Analytics for Profit Maximization in Time-Sensitive E-Commerce Retailing’.

 

In this work, we propose a prescriptive approach for designing a middle mile consolidation network that aims to maximize the profit of large e-commerce retailers. We embed lead-time dependent sales volume predictions into a new mixed-integer program (MIP) that determines shipment lead times and consolidation plans to maximize sales revenue net logistics cost. The MIP extends traditional flat network designs to capture waiting delays between load dispatches and ensure that shipment lead-time requirements are satisfied with a desired probability. We propose a solution approach that uses an IP-based local search and dynamic lead-time selection to find excellent consolidation plans for large, practically-sized instances. Computational experiments using data from a large U.S.-based e-commerce partner specializing in large and bulky items demonstrate the significant impact of flexible lead-time selection on the structure of the consolidation network designs and their concomitant operating costs. This work is joint with Lacy Greening, Jisoo Park, Alan Erera, and Benoit Montreuil.