Traffic Shaping in E-Commercial Search Engine: Multi-Objective Online Welfare Maximization

Authors

  • Liucheng Sun Alibaba Group Zhejiang University
  • Chenwei Weng Alibaba Group
  • Chengfu Huo Alibaba Group
  • Weijun Ren Alibaba Group
  • Guochuan Zhang Zhejiang University
  • Xin Li Alibaba Group

Keywords:

Business/Marketing/Advertising/E-commerce, Auctions and Market-Based Systems, Planning under Uncertainty

Abstract

The e-commercial search engine is the primary gateway for customers to find desired products and engage in online shopping. Besides displaying items to optimize for a single objective (i.e., relevance), ranking items needs to satisfy some other business requirements in practice. Recently, traffic shaping was introduced to incorporate multiple objectives in a constrained optimization framework. However, many practical business requirements can not explicitly represented by linear constraints as in the existing work, and this may limit the scalablity of their framework. This paper presents a unified framework from the aspect of multi-objective welfare maximization where we regard all business requirements as objectives to optimize. Our framework can naturally incorporate a wide range of application-driven requirements. In addition to formulating the problem, we design an online traffic splitting algorithm that allows us to flexibly adjust the priorities of different objectives, and it has rigorous theoretical guarantees over the adversarial scenario. We also run experiments on both synthetic and real-world datasets to validate our algorithms.

Downloads

Published

2021-05-18

How to Cite

Sun, L., Weng, C., Huo, C., Ren, W., Zhang, G., & Li, X. (2021). Traffic Shaping in E-Commercial Search Engine: Multi-Objective Online Welfare Maximization. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 574-581. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16136

Issue

Section

AAAI Technical Track on Application Domains