AAII Research Seminar Series | Seminar 1: Dr Peijun Guo
The UTS AAII Research Seminar Series | Seminar 1
The UTS AAII Research Seminar series is dedicated to fostering an engaging, inclusive, and interdisciplinary environment for internal and external AI researchers to share research ideas and findings in person. Our goal is to promote cross-lab communications and achieve visionary collaborations.
The series will encompass a wide range of AI topics, spanning from theoretical foundations to cutting-edge methodological development, cross-disciplinary applications, and insights from industry practices.
This monthly seminar series will offer valuable opportunities to invite world-renowned visiting scholars to share their latest research frontiers, mentor AAII’s middle and early career researchers with the guidance for research leadership, and educate HDR students to hone their presentation and communication skills to excel in their academic journeys.
Topic: 'Dynamic focus programming: A new approach to sequential decision problems under uncertainty'
Abstract: A new approach to sequential decision problems under uncertainty named dynamic focus programming is proposed with the focus theory of choice. In dynamic focus programming, there are two distinct evaluation systems: Positive and negative ones. Each possible path consisting of a decision sequence from the initial stage to the final stage and the associated states is examined. In the positive evaluation system, for each decision in the initial stage, if a path starting from it can bring about a relatively low total cost with a relatively high probability, then this path is selected as the positive focus path of this decision; based on the positive focus paths of all initial decisions, a decision maker chooses a most-preferred decision rule. In the negative evaluation system, for each decision in the initial stage, if a path starting from it can bring about a relatively high total cost with a relatively high probability, then this path is selected as the negative focus path of this decision; based on the negative focus paths of all initial decisions, a decision maker chooses a most acceptable decision rule.
There are distinct differences between stochastic dynamic programming and dynamic focus programming. Stochastic dynamic programming utilizes backward induction whereas dynamic focus programing uses forward calculation which is close to human being intuition. In stochastic dynamic programming, only a decision sequence can be obtained whereas in dynamic focus programming, a focus path is obtained. The focus path consists of not only a decision sequence from the initial stage to the final stage but also the associated states. The focus path provides the reason why such a decision sequence should be chosen. In addition, in dynamic focus programming framing effects can be handled by the positive and negative evaluation systems and the decision maker's personality and behavioral attributes can be properly accommodated by adjusting the parameters. Hence, dynamic focus programming makes the complicated decision-making procedure visible and no longer a black box.
We apply dynamic focus programming to a real bidding decision-making problem: We obtain the optimal decision rule and gain the behavioral insights of the decision maker.
Speaker: Dr Peijun Guo (Yokohama National University, Japan)
Dr. Peijun Guo is Professor of Decision Sciences, Faculty of Business Administration, Yokohama National University, Japan. He received the BE, ME and PhD in 1990, 1993 and 1996, respectively, all from Dalian University of Technology and the PhD in 2000 from Osaka Prefecture University majoring in industrial engineering supported by the Japanese government scholarship.
He was an Assistant Professor (2000–2001), an Associate Professor (2001–2007) in Faculty of Economics, Kagawa University, an Associate Professor (2007-2012), Professor (2012- ) in Faculty of Business Administration, Yokohama National University and a visiting scholar at SC Johnson College of Business, Cornell University (August 2017-June 2018).
His research interests involve operation research and management science, mainly in decision analysis under uncertainty. He proposes Focus Theory of Choice which models and axiomatizes a decision-making procedure under risk and uncertainty. It can account for many anomalies, including the St. Petersburg, Allais, and Ellsberg paradoxes, preference reversals, violations of stochastic dominance, violations of transitivity, the event-splitting effect, and the violation of tail-separability. Based on the focus theory of choice, he proposes the dynamic focus programming for sequential decision problems under uncertainty and the focus programming for static stochastic optimization problems (with Xide Zhu).
His papers also appear in European Journal of Operational Research, International Transactions in Operational Research, IEEE Transactions on SMC, Part A: Systems and Humans, Computational Statistics and Data Analysis, 4OR etc.
Prof. Guo is an Associate Editor of Information Sciences and the Editorial Board Members of several International Journals.
