ABSTRACT
Audience Look-alike Targeting is an online advertising technique in which an advertiser specifies a set of seed customers and tasks the advertising platform with finding an expanded audience of similar users. We will describe a two-stage embedding-based audience expansion model that is deployed in production at Pinterest. For the first stage we trained a global user embedding model on sitewide user activity logs. In the second stage, we use transfer learning and statistical techniques to create lightweight seed list representations in the embedding space for each advertiser. We create a (user, seed list) affinity scoring function that makes use of these lightweight advertiser representations. We describe the end-to-end system that computes and serves this model at scale. Finally, we propose an ensemble approach that combines single-advertiser classifiers with the embedding-based technique. We show offline evaluation and online experiments to prove that the expanded audience generated by the ensemble model has the best results for all seed list sizes.
- Alexandr Andoni and Piotr Indyk. 2008. Near-optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions. Commun. ACM, Vol. 51, 1 (Jan. 2008), 117--122. Google ScholarDigital Library
- Jeffrey Dean and Sanjay Ghemawat. 2008. MapReduce: Simplified Data Processing on Large Clusters. Commun. ACM , Vol. 51, 1 (Jan. 2008), 107--113. Google ScholarDigital Library
- Haishan Liu, David Pardoe, Kun Liu, Manoj Thakur, Frank Cao, and Chongzhe Li. 2016. Audience Expansion for Online Social Network Advertising. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16). ACM, New York, NY, USA, 165--174. Google ScholarDigital Library
- Haiyan Luo, Datong Chen, Zhen Xia, Shiyong Cheng, Yi Mao, Shu Zhang, Jiayi Wen, Xiaojiang Cheng, and Herve Marcellini. 2016. Methods and systems for near real-time lookalike audience expansion in ads targeting. Patent No. US20170330239A1, Filed May 13th., 2016, Issued Nov. 16th., 2017.Google Scholar
- Qiang Ma, Eeshan Wagh, Jiayi Wen, Zhen Xia, Robert Ormandi, and Datong Chen. 2016a. Score Look-Alike Audiences. In Data Mining Workshops (ICDMW), 2016 IEEE 16th International Conference on. 647--654.Google Scholar
- Qiang Ma, Musen Wen, Zhen Xia, and Datong Chen. 2016b. A Sub-linear, Massive-scale Look-alike Audience Extension System. In Proceedings of the 5th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications .Google Scholar
- Ashish Mangalampalli, Adwait Ratnaparkhi, Andrew O. Hatch, Abraham Bagherjeiran, Rajesh Parekh, and Vikram Pudi. 2011. A feature-pair-based associative classification approach to look-alike modeling for conversion-oriented user-targeting in tail campaigns. In Proceedings of the 20th international conference companion on World Wide Web (ACM). 85--86. Google ScholarDigital Library
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. CoRR , Vol. abs/1301.3781 (2013). arxiv: 1301.3781 http://arxiv.org/abs/1301.3781Google Scholar
- Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In Empirical Methods in Natural Language Processing (EMNLP). 1532--1543. http://www.aclweb.org/anthology/D14--1162Google Scholar
- C. Perlich, B. Dalessandro, T. Raeder, O. Stitelman, and F. Provost. 2014. Machine learning for targeted display advertising: transfer learning in action. Machine Learning , Vol. 95, 1 (01 Apr 2014), 103--127. Google ScholarDigital Library
- Yan Qu, Jing Wang, Yang Sun, and Hans Marius Holtan. 2014. Systems and methods for generating expanded user segments. Patent No. US8655695B1, Filed May 7th., 2010, Issued Feb. 18th., 2014.Google Scholar
- Jianqiang Shen, Sahin Cem Geyik, and Ali Dasdan. 2015. Effective Audience Extension in Online Advertising. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '15). ACM, New York, NY, USA, 2099--2108. Google ScholarDigital Library
- Vassilis Stoumpos and Alex Delis. 2009. Fragment and replicate algorithms for non-equi-join evaluation on Smart Disks. In Autonomous Decentralized Systems, 2009. ISADS'09. International Symposium on. IEEE, 1--8.Google ScholarCross Ref
- Ledell Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, and Jason Weston. 2017. StarSpace: Embed All The Things! CoRR , Vol. abs/1709.03856 (2017). arxiv: 1709.03856 http://arxiv.org/abs/1709.03856Google Scholar
Index Terms
- Finding Users Who Act Alike: Transfer Learning for Expanding Advertiser Audiences
Recommendations
Volume Ranking and Sequential Selection in Programmatic Display Advertising
CIKM '17: Proceedings of the 2017 ACM on Conference on Information and Knowledge ManagementProgrammatic display advertising, which enables advertisers to make real-time decisions on individual ad display opportunities so as to achieve a precise audience marketing, has become a key technique for online advertising. However, the constrained ...
Let users tell the story: evaluating user experience with experience reports
CHI EA '10: CHI '10 Extended Abstracts on Human Factors in Computing SystemsUser experience (UX) has been under extensive research in recent years. One of the key questions has been how to evaluate user experience. Several methods such as diaries, experience sampling and questionnaires have been used for collecting data on user ...
Comments