ABSTRACT
A number of transportation studies have adopted data-driven optimization approaches. Most of the studies employ a two-step approach: in the first step, machine learning models are used to predict the values of uncertain parameters; in the second step, the predicted values are used as input for an optimization model to derive a decision. However, such a two-step approach is flawed in several aspects. In the past three years, we have witnessed a number of methodological developments in the operations research literature that address the deficiencies of the two-step approach. This seminar will introduce a few of the methodological techniques that are widely applicable in practice and easy to implement by those without much operations research background.
INTRODUCTION
Dr. Wang is currently Professor at The Hong Kong Polytechnic University (PolyU). Prior to joining PolyU, he worked as a faculty member at Old Dominion University, USA, and the University of Wollongong, Australia. Dr. Wang’s research interests include big data in shipping, urban transport network modeling, and logistics and supply chain management. Dr. Wang has published a total of 40 papers in Transportation Research Part B, Transportation Science, Management Science, and Operations Research. Dr. Wang is a co-editor-in-chief of Transportation Research Part E, an editor-in-chief of Cleaner Logistics and Supply Chain and Communications in Transportation Research, an associate editor of Flexible Services and Manufacturing Journal, Transportmetrica A, and Transportation Letters, a handle editor of Transportation Research Record, an editorial board editor of Transportation Research Part B, and an editorial board member of Maritime Transport Research. Dr. Wang dedicates to rethinking and proposing innovative solutions to improve the efficiency of maritime and urban transportation systems, to promote environmentally friendly and sustainable practices, and to transform business and engineering education