ABSTRACT
Web-based ranking problems involve ordering different kinds of items in a list or grid to be displayed in mediums like a website or a mobile app. In most cases, there are multiple objectives or metrics like clicks, viral actions, job applications, advertising revenue and others that we want to balance. Constructing a serving algorithm that achieves the desired tradeoff among multiple objectives is challenging, especially for more than two objectives. In addition, it is often not possible to estimate such a serving scheme using offline data alone for non-stationary systems with frequent online interventions. We consider a large-scale online application where metrics for multiple objectives are continuously available and can be controlled in a desired fashion by changing certain control parameters in the ranking model. We assume that the desired balance of metrics is known from business considerations. Our approach models the balance criteria as a composite utility function via a Gaussian process over the space of control parameters. We show that obtaining a solution can be equated to finding the maximum of the Gaussian process, practically obtainable via Bayesian optimization. However, implementing such a scheme for large-scale applications is challenging. We provide a novel framework to do so and illustrate its efficacy in the context of LinkedIn Feed. In particular, we show the effectiveness of our method by using both offline simulations as well as promising online A/B testing results. At the time of writing this paper, the method described was fully deployed on the LinkedIn Feed.
Supplemental Material
- Deepak Agarwal, Bee-Chung Chen, Pradheep Elango, and Xuanhui Wang. 2011. Click Shaping to Optimize Multiple Objectives. In KDD. ACM, New York, NY, USA, 132--140. Google ScholarDigital Library
- Deepak Agarwal, Bee-Chung Chen, Pradheep Elango, and Xuanhui Wang. 2012. Personalized Click Shaping Through Lagrangian Duality for Online Recommendation SIGIR. ACM, New York, NY, USA, 485--494. Google ScholarDigital Library
- Deepak Agarwal, Bee-Chung Chen, Rupesh Gupta, Joshua Hartman, Qi He, Anand Iyer, Sumanth Kolar, Yiming Ma, Pannagadatta Shivaswamy, Ajit Singh, and Liang Zhang. 2014. Activity Ranking in LinkedIn Feed. In KDD. ACM, New York, NY, USA, 1603--1612. Google ScholarDigital Library
- Deepak Agarwal, Bee-Chung Chen, Qi He, Zhenhao Hua, Guy Lebanon, Yiming Ma, Pannagadatta Shivaswamy, Hsiao-Ping Tseng, Jaewon Yang, and Liang Zhang. 2015. Personalizing LinkedIn Feed. In KDD. ACM, New York, NY, USA, 1651--1660. Google ScholarDigital Library
- Shipra Agrawal and Navin Goyal. 2012. Analysis of Thompson Sampling for the Multi-armed Bandit Problem Proceedings of the 25th Annual Conference on Learning Theory (Proceedings of Machine Learning Research), bibfieldeditorShie Mannor, Nathan Srebro, and Robert C. Williamson (Eds.), Vol. Vol. 23. PMLR, Edinburgh, Scotland, 39.1--39.26.Google Scholar
- Shipra Agrawal and Navin Goyal. 2013. Thompson Sampling for Contextual Bandits with Linear Payoffs ICML. JMLR.org, USA, 1220--1228. Google ScholarDigital Library
- Shipra Agrawal and Navin Goyal. 2017. Near-Optimal Regret Bounds for Thompson Sampling. J. ACM, Vol. 64, 5 (Sept.. 2017), 30:1--30:24. 1933. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, Vol. 25, 3/4 (1933), 285--294. Google ScholarDigital Library
- Jarno Vanhatalo, Jaakko Riihimaki, Jouni Hartikainen, Pasi Jylanki, Ville Tolvanen, and Aki Vehtari. 2013. GPstuff: Bayesian Modeling with Gaussian Processes. J. Mach. Learn. Res., Vol. 14, 1 (April. 2013), 1175--1179. showISSN1532--4435 Google ScholarDigital Library
Index Terms
- Online Parameter Selection for Web-based Ranking Problems
Recommendations
First workshop on targeting and ranking for online advertising
WWW '08: Proceedings of the 17th international conference on World Wide WebOnline advertising is a rapidly growing, multi-billion dollar industry. It has become a significant element of the Web browsing experience. Online advertising providers use sophisticated ad targeting and ranking algorithms with the dual aim of ...
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 ...
A framework for intermediated online targeted advertising with banner ranking mechanism
Reinforced by the fast growth of electronic commerce, even during the current global economic downturn, intermediated online targeted advertising (IOTA) has emerged as a promising electronic business model empowered by the Web 2.0 principle. IOTA ...
Comments