Don't Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting

Yi Feng, Ting Wang, Chuanyi Li, Vincent Ng, Jidong Ge, Bin Luo, Yucheng Hu and Xiaopeng Zhang.
Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 1493-1503, 2021.

Click here for the PDF version.

Abstract

User targeting is an essential task in the modern advertising industry: given a package of ads for a particular category of products (e.g., green tea), identify the online users to whom the ad package should be targeted. A (ad package specific) user targeting model is typically trained using historical clickthrough data: positive instances correspond to users who have clicked on an ad in the package before, whereas negative instances correspond to users who have not clicked on any ads in the package that were displayed to them. Collecting a sufficient amount of positive training data for training an accurate user targeting model, however, is by no means trivial. This paper proposes a novel method for automatic augmentation of the set of positive training instances. Experimental results on two datasets, including a real-world company dataset, demonstrate the effectiveness of our proposed method.

BibTeX entry

@InProceedings{Feng+etal:21a,
  author = {Yi Feng and Ting Wang and Chuanyi Li and Vincent Ng and Jidong Ge and Bin Luo and Yucheng Hu and Xiaopeng Zhang},
  title = {Don't Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},
  pages = {1493--1503},
  year = 2021}