A Non-Parametric Data-Driven Approach to Inventory Planning and Revenue Management

Information and Operations Management Department, Marshall School of Business Seminarby Dr. Woonghee Tim HuhIEOR Department, Columbia UniversityABSTRACT: We consider inventory planning and revenue management problems where the distribution of demand distribution is not available a priori, and lost sales are not observable. We take a non-parametric approach, and propose adaptive algorithms that generate a sequence of ordering decisions over time, where the decision in each period depends only on historical sales data. We show that our adaptive algorithms converge to the optimal solution, and establish the convergence rate.This is a joint work with Paat Rusmevichientong.Woonghee Tim Huh is an assistant professor in the Department of Industrial Engineering and Operations Research at Columbia University. His current research interests include developing data-driven adaptive policies, and proving structural results in the inventory theory such as the optimality of threshold policies. He has received Columbia Engineering School's Distinguished Teaching Award and the Diversity Teaching Award. He recieived a B.A. in sociology, B.Math in computer science and M.Math in combinatorics & optimization and from the University of Waterloo, and holds an M.Sc. and a Ph.D. in Operations Research from Cornell University.Friday, September 22, 2006, Hoffman Hall 303, 1:30 - 3:00 PM

Location: Hoffman Hall 303

Audiences: Everyone Is Invited

Contact: Georgia Lum