主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2025, Vol. 33 ›› Issue (8): 230-237.doi: 10.16381/j.cnki.issn1003-207x.2022.1769

• • 上一篇    

考虑不确定协变量下的在线广告鲁棒分配策略

代文强(), 李丹阳   

  1. 电子科技大学经济与管理学院,四川 成都 611731
  • 收稿日期:2022-08-12 修回日期:2022-12-18 出版日期:2025-08-25 发布日期:2025-09-10
  • 通讯作者: 代文强 E-mail:wqdai@uestc.edu.cn
  • 基金资助:
    国家自然科学基金项目(71871045)

Robust Guaranteed Delivery and Allocation Optimization for Online Display Advertising with Covariate-based Information

Wenqiang Dai(), Danyang Li   

  1. School of Management and Economics,University of Electronic Science and Technology of China,Chengdu 611731,China
  • Received:2022-08-12 Revised:2022-12-18 Online:2025-08-25 Published:2025-09-10
  • Contact: Wenqiang Dai E-mail:wqdai@uestc.edu.cn

摘要:

本文提出具有不确定协变量信息和目标群体曝光供应量条件下的在线广告库存分配模型。由于精确获知目标群体的曝光供应量和协变量信息的联合随机概率分布相当困难,采用分布鲁棒优化方法进行建模。在已有研究的基础上,首先构建包含协变量信息的联合随机分布模糊集,并考虑基于该模糊集最坏情形下服务水平联合机会约束随机优化模型。利用锥对偶的方法给出了求解算法,进行了仿真分析,验证了模型和算法的有效性。同时,给出了管理学启示。

关键词: 在线广告, 分布鲁棒优化, 协变量, 保量合约

Abstract:

An online advertising contract inventory allocation model is proposed, in which covariate information is incorporated and the impression supply of targeted viewers is treated as uncertain. Owing to the fact that the joint probability distribution of viewer impression supply and covariate information is difficult to be precisely known, the model is constructed by means of a distributionally robust optimization approach. Building upon existing research, an ambiguity set based on covariate information is first formulated; subsequently, an exact algorithm is derived through the utilization of dual cone techniques. The validity of the proposed model is ultimately demonstrated via simulation experiments. Furthermore, managerial implications are provided.

Key words: online advertising, distributionally robust optimization, covariate information, guaranteed contract

中图分类号: