Cost-Restricted Feature Selection for Data Acquisition

• 成果类型: Article
• 署名作者: Liu, Xiaoping; Li, Xiao-Bai; Sarkar, Sumit
• 署名单位: Northeastern University; University of Massachusetts System; University of Massachusetts Lowell; University of Texas System; University of Texas Dallas
• 刊物名称: MANAGEMENT SCIENCE
• ISSN/ISSBN: 0025-1909
• DOI: 10.1287/mnsc.2022.4551
• 发表日期: 2023
• 页码: 3976-3992
• 关键词: data acquisition; feature selection; Lasso; Linear Regression; logistic regression

摘要

When acquiring consumer data for marketing or new business initiatives, it is important to decide what attributes or features of potential customers should be acquired. We study a new feature selection problem in the context of customer data acquisition in which different features have different acquisition costs. This feature selection problem is studied for linear regression and logistic regression. We formulate the feature selection and acquisition problems as nonlinear discrete optimization problems that minimize prediction errors subject to a budget constraint. We derive the analytical properties of the solutions for the problems, develop a computational procedure for solving the problems, provide an intuitive interpretation for the feature selection criteria, and discuss managerial implications of the solution approach. The results of the experimental study demonstrate the effectiveness of our approach.