A Sub-linear, Massive-scale Look-alike Audience Extension System A Massive-scale Look-alike Audience Extension

Qiang Ma, Musen Wen, Zhen Xia, Datong Chen
Proceedings of the 5th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications at KDD 2016, PMLR 53:51-67, 2016.

Abstract

Look-alike audience extension is a practically effective way to customize high-performance audience in on-line advertising. With look-alike audience extension system, any advertiser can easily generate a set of customized audience by just providing a list of existing customers without knowing the detailed targetable attributes in a sophisticated advertising system. In this paper, we present our newly developed graph-based look-alike system in Yahoo! advertising platform which provides look-alike audiences for thousands of campaigns. Extensive experiments have been conducted to compare our look-alike model with three other existing look-alike systems using billions of users and millions of user features. The experiment results show that our developed graph-based method with nearest-neighbor filtering outperforms other methods by more than 50% regarding conversion rate in app-install ad campaigns.

Cite this Paper

BibTeX
@InProceedings{pmlr-v53-ma16, title = {A Sub-linear, Massive-scale Look-alike Audience Extension System A Massive-scale Look-alike Audience Extension}, author = {Ma, Qiang and Wen, Musen and Xia, Zhen and Chen, Datong}, booktitle = {Proceedings of the 5th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications at KDD 2016}, pages = {51--67}, year = {2016}, editor = {Fan, Wei and Bifet, Albert and Read, Jesse and Yang, Qiang and Yu, Philip S.}, volume = {53}, series = {Proceedings of Machine Learning Research}, address = {San Francisco, California, USA}, month = {14 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v53/ma16.pdf}, url = {https://proceedings.mlr.press/v53/ma16.html}, abstract = {Look-alike audience extension is a practically effective way to customize high-performance audience in on-line advertising. With look-alike audience extension system, any advertiser can easily generate a set of customized audience by just providing a list of existing customers without knowing the detailed targetable attributes in a sophisticated advertising system. In this paper, we present our newly developed graph-based look-alike system in Yahoo! advertising platform which provides look-alike audiences for thousands of campaigns. Extensive experiments have been conducted to compare our look-alike model with three other existing look-alike systems using billions of users and millions of user features. The experiment results show that our developed graph-based method with nearest-neighbor filtering outperforms other methods by more than 50% regarding conversion rate in app-install ad campaigns.} }
Endnote
%0 Conference Paper %T A Sub-linear, Massive-scale Look-alike Audience Extension System A Massive-scale Look-alike Audience Extension %A Qiang Ma %A Musen Wen %A Zhen Xia %A Datong Chen %B Proceedings of the 5th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications at KDD 2016 %C Proceedings of Machine Learning Research %D 2016 %E Wei Fan %E Albert Bifet %E Jesse Read %E Qiang Yang %E Philip S. Yu %F pmlr-v53-ma16 %I PMLR %P 51--67 %U https://proceedings.mlr.press/v53/ma16.html %V 53 %X Look-alike audience extension is a practically effective way to customize high-performance audience in on-line advertising. With look-alike audience extension system, any advertiser can easily generate a set of customized audience by just providing a list of existing customers without knowing the detailed targetable attributes in a sophisticated advertising system. In this paper, we present our newly developed graph-based look-alike system in Yahoo! advertising platform which provides look-alike audiences for thousands of campaigns. Extensive experiments have been conducted to compare our look-alike model with three other existing look-alike systems using billions of users and millions of user features. The experiment results show that our developed graph-based method with nearest-neighbor filtering outperforms other methods by more than 50% regarding conversion rate in app-install ad campaigns.
RIS
TY - CPAPER TI - A Sub-linear, Massive-scale Look-alike Audience Extension System A Massive-scale Look-alike Audience Extension AU - Qiang Ma AU - Musen Wen AU - Zhen Xia AU - Datong Chen BT - Proceedings of the 5th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications at KDD 2016 DA - 2016/12/06 ED - Wei Fan ED - Albert Bifet ED - Jesse Read ED - Qiang Yang ED - Philip S. Yu ID - pmlr-v53-ma16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 53 SP - 51 EP - 67 L1 - http://proceedings.mlr.press/v53/ma16.pdf UR - https://proceedings.mlr.press/v53/ma16.html AB - Look-alike audience extension is a practically effective way to customize high-performance audience in on-line advertising. With look-alike audience extension system, any advertiser can easily generate a set of customized audience by just providing a list of existing customers without knowing the detailed targetable attributes in a sophisticated advertising system. In this paper, we present our newly developed graph-based look-alike system in Yahoo! advertising platform which provides look-alike audiences for thousands of campaigns. Extensive experiments have been conducted to compare our look-alike model with three other existing look-alike systems using billions of users and millions of user features. The experiment results show that our developed graph-based method with nearest-neighbor filtering outperforms other methods by more than 50% regarding conversion rate in app-install ad campaigns. ER -
APA
Ma, Q., Wen, M., Xia, Z. & Chen, D.. (2016). A Sub-linear, Massive-scale Look-alike Audience Extension System A Massive-scale Look-alike Audience Extension. Proceedings of the 5th International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications at KDD 2016, in Proceedings of Machine Learning Research 53:51-67 Available from https://proceedings.mlr.press/v53/ma16.html.

Related Material