跳到主要导航 跳到搜索 跳到主要内容

EdgeNet: Encoder decoder generative Network for Auction Design in E-commerce Online Advertising

  • Guangyuan Shen
  • , Duanxiao Song
  • , Shenjie Sun
  • , Libin Yang
  • , Dehong Gao
  • , Zhen Wang
  • , Yongping Shi
  • , Wei Ning
  • Northwestern Polytechnical University Xian
  • Alibaba Group Holding Ltd.
  • Shanghai Jiao Tong University

科研成果: 书/报告/会议事项章节会议稿件同行评审

5 引用 (Scopus)

摘要

We present a new encoder-decoder generative network dubbed EdgeNet, which introduces a novel encoder-decoder framework for data-driven auction design in online e-commerce advertising. We break the neural auction paradigm of Generalized-Second-Price (GSP) and improve the utilization efficiency of data while ensuring the economic characteristics of the auction mechanism. Specifically, EdgeNet introduces a transformer-based encoder to better capture the mutual influence among different candidate advertisements. In contrast to GSP based neural auction model, we design an auto-regressive decoder to better utilize the rich context information in online advertising auctions. EdgeNet is conceptually simple and easy to extend to the existing end-to-end neural auction framework. We validate the efficiency of EdgeNet on a wide range of e-commercial advertising auctions, demonstrating its potential in improving user experience and platform revenue.

源语言英语
主期刊名CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
出版商Association for Computing Machinery
4274-4278
页数5
ISBN(电子版)9798400701245
DOI
出版状态已出版 - 21 10月 2023
活动32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, 英国
期限: 21 10月 202325 10月 2023

丛书

姓名International Conference on Information and Knowledge Management, Proceedings

会议

会议32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
国家/地区英国
Birmingham
时期21/10/2325/10/23

学术指纹

探究 'EdgeNet: Encoder decoder generative Network for Auction Design in E-commerce Online Advertising' 的科研主题。它们共同构成独一无二的学术指纹。

引用此