报告简介：We propose a preference learning algorithm for uncovering Decision Makers' (DMs') contingent evaluation strategies in the context of multiple criteria sorting. We assume the preference information in the form of holistic assignment examples derived from the analysis of alternatives' performance vectors and textual descriptions. We characterize the decision policies using a mixture of threshold-based value-driven preference models and associated latent topics. The latter serve as the stimuli underlying the contingency in decision behavior, providing a transparent and interpretable way to explore and understand DM's contingent preferences. Such a probabilistic model is constructed using a flexible and nonparametric Bayesian framework. The proposed method adopts a hierarchical Dirichlet process so that a group of DMs can share a countably infinite number of contingent models and topics. For all DMs, it automatically identifies the components representing their evaluation strategies adequately. The posterior is summarized using the Hamiltonian Monte Carlo sampling method. The experimental results indicate that our approach performs favorably in both interpreting DM's contingent decision behavior and recommending decisions on new alternatives.
报告人简介：刘佳鹏博士，西安交通大学管理学院信息管理与电子商务系、智能决策与机器学习研究中心副教授、博士生导师，研究方向包括决策分析、机器学习、贝叶斯方法、大数据模型，主持过国家自然科学基金青年项目、面上项目以及博士后科学基金项目。研究工作发表在INFORMS Journal on Computing、European Journal of Operational Research、Omega、系统工程理论与实践等国内外重要学术期刊上。