报告人: 马萨诸塞大学洛厄尔分校 李晓白 教授
We study strategically missing data problems in predictive analytics with regression. In many real-world situations, such as financial reporting, college admission, job application, and marketing advertisement, data providers often hide certain information on purpose in order to gain a favorable outcome. It is important for the decision maker to have a mechanism to deal with such strategic behaviors. We propose a novel approach, based on the Support Vector Regression (SVR) technique, to handle strategically missing data in regression prediction. The proposed method derives the imputed values of missing data based on the margins of the SVR models. It provides incentives for the data providers to disclose their true information. We show that imputation errors for the missing values are minimized under some reasonable conditions. Furthermore, with the proposed method, the decision maker’s decision models will not be affected by strategic behaviors of data providers. An experimental study on real-world data demonstrates the effectiveness of the proposed approach.
Dr. Xiaobai Li is a Professor of Information Systems in the Department of Operations and Information Systems at the University of Massachusetts Lowell, USA. He received his Ph.D. in management science from the University of South Carolina. Dr. Li’s research focuses on data science, business analytics, data privacy, and information economics. He has received funding for his research from National Institutes of Health (NIH) and National Science Foundation (NSF), USA. His work has appeared in Management Science, Information Systems Research, MIS Quarterly, Operations Research, INFORMS Journal on Computing, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Systems, Man, and Cybernetics, Decision Support Systems, Communications of the ACM, and European Journal of Operational Research, among others. He is serving as Associate Editor for Information Systems Research, Decision Support Systems, and ACM Journal of Data and Information Quality.