ABSTRACT
The ad-ranking module is the core of the advertising recommender system. Existing ad-ranking modules are mainly based on the deep neural network click-through rate prediction model. Recently an innovative ad-ranking paradigm called DNN-MAB has been introduced to address DNN-only paradigms’ weakness in perceiving highly dynamic user intent over time. We introduce the DNN-MAB paradigm into our ad-ranking system to alleviate the Matthew effect that harms the user experience. Due to data sparsity, however, the actual performance of DNN-MAB is lower than expected. In this paper, we propose an innovative ad-ranking paradigm called DNN-VMAB to solve these problems. Based on vectorization and clustering, it utilizes latent collaborative information in user behavior data to find a set of ads with higher relativity and diversity. As an integration of the essences of classical collaborative filtering, deep click-through rate prediction model, and contextual multi-armed bandit, it can improve platform revenue and user experience. Both offline and online experiments show the advantage of our new algorithm over DNN-MAB and some other existing algorithms.
- Peter Auer. 2002. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research 3, Nov (2002), 397–422.Google ScholarDigital Library
- Guy Bresler, George H Chen, and Devavrat Shah. 2014. A latent source model for online collaborative filtering. In Advances in Neural Information Processing Systems. 3347–3355.Google Scholar
- Yufei Feng, Fuyu Lv, Weichen Shen, Menghan Wang, Fei Sun, Yu Zhu, and Keping Yang. 2019. Deep Session Interest Network for Click-Through Rate Prediction. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. 2301–2307.Google ScholarCross Ref
- Claudio Gentile, Shuai Li, Purushottam Kar, Alexandros Karatzoglou, Giovanni Zappella, and Evans Etrue. 2017. On context-dependent clustering of bandits. In Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 1253–1262.Google ScholarDigital Library
- Claudio Gentile, Shuai Li, and Giovanni Zappella. 2014. Online clustering of bandits. In International Conference on Machine Learning. 757–765.Google Scholar
- Branislav Kveton, Csaba Szepesvari, Zheng Wen, and Azin Ashkan. 2015. Cascading bandits: Learning to rank in the cascade model. In International Conference on Machine Learning. 767–776.Google Scholar
- Chang Li, Branislav Kveton, Tor Lattimore, Ilya Markov, Maarten de Rijke, Csaba Szepesvári, and Masrour Zoghi. 2019. BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback. In Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence. 47.Google Scholar
- Shuai Li, Claudio Gentile, and Alexandros Karatzoglou. 2016. Graph clustering bandits for recommendation. arXiv preprint arXiv:1605.00596(2016).Google Scholar
- Shuai Li, Alexandros Karatzoglou, and Claudio Gentile. 2016. Collaborative filtering bandits. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. ACM, 539–548.Google ScholarDigital Library
- Yudan Liu, Kaikai Ge, Xu Zhang, and Leyu Lin. 2019. Real-time Attention Based Look-alike Model for Recommender System. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2765–2773.Google ScholarDigital Library
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111–3119.Google Scholar
- Trong T Nguyen and Hady W Lauw. 2014. Dynamic clustering of contextual multi-armed bandits. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. ACM, 1959–1962.Google ScholarDigital Library
- Javier Sanz-Cruzado, Pablo Castells, and Esther López. 2019. A simple multi-armed nearest-neighbor bandit for interactive recommendation. In Proceedings of the 13th ACM Conference on Recommender Systems. ACM, 358–362.Google ScholarDigital Library
- Aleksandrs Slivkins, Filip Radlinski, and Sreenivas Gollapudi. 2013. Ranked bandits in metric spaces: learning diverse rankings over large document collections. Journal of Machine Learning Research 14, Feb (2013), 399–436.Google ScholarDigital Library
- Stephan Ten Hagen, Maarten Van Someren, Vera Hollink, 2003. Exploration/exploitation in adaptive recommender systems. proceedings of Eunite 2003(2003).Google Scholar
- Ruoxi Wang, Bin Fu, Gang Fu, and Mingliang Wang. 2017. Deep & cross network for ad click predictions. In Proceedings of the ADKDD’17. ACM, 12.Google ScholarDigital Library
- Christopher John Cornish Hellaby Watkins. 1989. Learning from Delayed Rewards. Ph.D. Dissertation. King’s College, Cambridge, UK. http://www.cs.rhul.ac.uk/~chrisw/new_thesis.pdfGoogle Scholar
- Yan Yan, Zitao Liu, Meng Zhao, Wentao Guo, Weipeng P Yan, and Yongjun Bao. 2018. A Practical Deep Online Ranking System in E-commerce Recommendation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 186–201.Google Scholar
Index Terms
- A Joint Dynamic Ranking System with DNN and Vector-based Clustering Bandit
Recommendations
A Practical Deep Online Ranking System in E-commerce Recommendation
Machine Learning and Knowledge Discovery in DatabasesAbstractUser online shopping experience in modern e-commerce websites critically relies on real-time personalized recommendations. However, building a productionized recommender system still remains challenging due to a massive collection of items, a huge ...
Joint Collaborative Ranking with Social Relationships in Top-N Recommendation
CIKM '16: Proceedings of the 25th ACM International on Conference on Information and Knowledge ManagementWith the advent of learning to rank methods, relevant studies showed that Collaborative Ranking (CR) models can produce accurate ranked lists in the top-N recommendation problem. However, in practice several real-world problems decrease their ranking ...
Predicting User Engagement in Twitter with Collaborative Ranking
RecSysChallenge '14: Proceedings of the 2014 Recommender Systems ChallengeCollaborative Filtering (CF) is a core component of popular web-based services such as Amazon, YouTube, Netflix, and Twitter. Most applications use CF to recommend a small set of items to the user. For instance, YouTube presents to a user a list of top-...
Comments