Conglong Li
David G. Andersen
ABSTRACT
Search advertising depends on accurate predictions of user behavior and interest, accomplished today using complex and computationally expensive machine learning algorithms that estimate the potential revenue gain of thousands of candidate advertisements per search query. The accuracy of this estimation is important for revenue, but the cost of these computations represents a substantial expense, e.g., 10% to 30% of the total gross revenue. Caching the results of previous computations is a potential path to reducing this expense, but traditional domain-agnostic and revenue-agnostic approaches to do so result in substantial revenue loss. This paper presents three domain-specific caching mechanisms that successfully optimize for both factors. Simulations on a trace from the Bing advertising system show that a traditional cache can reduce cost by up to 27.7% but has negative revenue impact as bad as -14.1%. On the other hand, the proposed mechanisms can reduce cost by up to 20.6% while capping revenue impact between -1.3% and 0%. Based on Microsoft's earnings release for FY16 Q4, the traditional cache would reduce the net profit of Bing Ads by $84.9 to $166.1 million in the quarter, while our proposed cache could increase the net profit by $11.1 to $71.5 million.
- 2016. Average CTR (Click-Through Rate): Learn How Your CTR Compares. http://www.wordstream.com/average-ctr. (2016).Google Scholar
- 2017. Microsoft Earnings Release FY16 Q4. https://www.microsoft.com/en-us/Investor/earnings/FY-2016-Q4/. (2017).Google Scholar
- Sadiye Alici, Ismail Sengor Altingovde, Rifat Ozcan, Berkant Barla Cambazoglu, and Özgür Ulusoy. 2011. Timestamp-based Result Cache Invalidation for Web Search Engines. In Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. Google ScholarDigital Library
- Sadiye Alici, Ismail Sengor Altingovde, Rifat Ozcan, B. Barla Cambazoglu, and Özgür Ulusoy. 2012. Adaptive Time-to-Live Strategies for Query Result Caching in Web Search Engines. In Proceedings of the 34th European Conference on Information Retrieval. Google ScholarDigital Library
- Ricardo Baeza-Yates, Aristides Gionis, Flavio P Junqueira, Vanessa Murdock, Vassilis Plachouras, and Fabrizio Silvestri. 2008. Design Trade-Offs for Search Engine Caching. ACM Trans. Web 2, 4 (Oct. 2008).Google ScholarDigital Library
- Xiao Bai and Flavio P. Junqueira. 2012. Online Result Cache Invalidation for Real-time Web Search. In Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval. Google ScholarDigital Library
- Edward Bortnikov, Ronny Lempel, and Kolman Vornovitsky. 2011. Caching for Realtime Search. In Proceedings of the 33rd European Conference on Information Retrieval. Google ScholarDigital Library
- B Barla Cambazoglu and Ismail Sengor Altingovde. 2012. Impact of Regionalization on Performance of Web Search Engine Result Caches. In Proceedings of the 19th Symposium on String Processing and Information Retrieval. Google ScholarDigital Library
- Berkant Barla Cambazoglu, Flavio P. Junqueira, Vassilis Plachouras, Scott Banachowski, Baoqiu Cui, Swee Lim, and Bill Bridge. 2010. A Refreshing Perspective of Search Engine Caching. In Proceedings of the 19th International Conference on World Wide Web. Google ScholarDigital Library
- Pei Cao and Sandy Irani. 1997. Cost-aware WWW Proxy Caching Algorithms. In Proceedings of the USENIX Symposium on Internet Technologies and Systems.Google ScholarDigital Library
- Tiziano Fagni, Raffaele Perego, Fabrizio Silvestri, and Salvatore Orlando. 2006. Boosting the Performance of Web Search Engines: Caching and Prefetching Query Results by Exploiting Historical Usage Data. ACM Trans. Information Systems 24, 1 (Jan. 2006). Google ScholarDigital Library
- Qingqing Gan and Torsten Suel. 2009. Improved Techniques for Result Caching in Web Search Engines. In Proceedings of the 18th International Conference on World Wide Web. Google ScholarDigital Library
- Thore Graepel, Joaquin Q. Candela, Thomas Borchert, and Ralf Herbrich. 2010. Web-Scale Bayesian Click-Through Rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine. In Proceedings of the 27th international conference on machine learning.Google ScholarDigital Library
- Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yanxin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers, and Joaquin Quiñonero Candela. 2014. Practical Lessons from Predicting Clicks on Ads at Facebook. In Proceedings of the Eighth International Workshop on Data Mining for Online Advertising. Google ScholarDigital Library
- Conglong Li and Alan L. Cox. 2015. GD-Wheel: A Cost-aware Replacement Policy for Key-value Stores. In Proceedings of the Tenth European Conference on Computer Systems. Google ScholarDigital Library
- H. Brendan McMahan, Gary Holt, D. Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, Sharat Chikkerur, Dan Liu, Martin Wattenberg, Arnar Mar Hrafnkelsson, Tom Boulos, and Jeremy Kubica. 2013. Ad Click Prediction: A View from the Trenches. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Google ScholarDigital Library
- Rifat Ozcan, Ismail Sengor Altingovde, B. Barla Cambazoglu, and Özgür Ulusoy. 2013. Second Chance: A Hybrid Approach for Dynamic Result Caching and Prefetching in Search Engines. ACM Trans. Web 8, 1 (Dec. 2013). Google ScholarDigital Library
- Rifat Ozcan, Ismail Sengor Altingovde, and Özgür Ulusoy. 2011. Cost-Aware Strategies for Query Result Caching in Web Search Engines. ACM Trans. Web 5, 2 (May 2011). Google ScholarDigital Library
- Fethi Burak Sazoglu, B. Barla Cambazoglu, Rifat Ozcan, Ismail Sengor Altingovde, and Özgür Ulusoy. 2013. A Financial Cost Metric for Result Caching. In Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. Google ScholarDigital Library
Index Terms
- Workload analysis and caching strategies for search advertising systems
Recommendations
Better Caching in Search Advertising Systems with Rapid Refresh Predictions
WWW '18: Proceedings of the 2018 World Wide Web ConferenceTo maximize profit and connect users to relevant products and services, search advertising systems use sophisticated machine learning algorithms to estimate the revenue expectations of thousands of matching ad listings per query. These machine learning ...
On the design of sponsored keyword advertising slot auctions: An analysis of a generalized second-price auction approach
The generalized second-priceauction mechanism is commonly used in research in the context of keyword advertising slot auctioning. The mechanism sets the clearing prices for advertising slots on a search engine's Web pages such that the advertiser will ...
An analysis of alternative slot auction designs for sponsored search
EC '06: Proceedings of the 7th ACM conference on Electronic commerceBillions of dollars are spent each year on sponsored search, a form of advertising where merchants pay for placement alongside web search results. Slots for ad listings are allocated via an auction-style mechanism where the higher a merchant bids, the ...
Comments