AiAds: Automated and Intelligent Advertising System for Sponsored Search

@article{Yang2019AiAdsAA,
  title={AiAds: Automated and Intelligent Advertising System for Sponsored Search},
  author={Xiao Yang and Daren Sun and Ruiwei Zhu and Tao Deng and Zhi Guo and Zongyao Ding and Shouke Qin and Yanfeng Zhu},
  journal={Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  year={2019}
}
  • Xiao Yang, Daren Sun, Yanfeng Zhu
  • Published 25 July 2019
  • Computer Science
  • Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Sponsored search has more than 20 years of history, and it has been proven to be a successful business model for online advertising. Based on the pay-per-click pricing model and the keyword targeting technology, the sponsored system runs online auctions to determine the allocations and prices of search advertisements. In the traditional setting, advertisers should manually create lots of ad creatives and bid on some relevant keywords to target their audience. Due to the huge amount of search… 

Figures and Tables from this paper

Beyond Keyword Targeting: An End-to-End Ad Retrieval Framework for Sponsored Search
TLDR
An end-to-end ad retrieval framework for sponsored search that can break the limits of keyword targeting and can achieve direct matching from query to related ads.
CHASE: Commonsense-Enriched Advertising on Search Engine with Explicit Knowledge
While online advertising is one of the major sources of income for search engines, pumping up the incomes from business advertisements while ensuring the user experience becomes a challenging but
A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising
TLDR
This paper investigates the competition and cooperation relation among auto-bidding agents, and proposes a temperature-regularized credit assignment to establish a mixed cooperative-competitive paradigm that outperforms several baseline methods in terms of social welfare and revenue.
Impression Pacing for Jobs Marketplace at LinkedIn
TLDR
An impression-based spend computation system that works via assigning a projected/expected charge amount each time a job is shown to the user, taking into account both the likelihood that the user will click the job, and the recommender system specific considerations such as the order within a page that a job was recommended.
Incentive Mechanism Design for ROI-constrained Auto-bidding
TLDR
This paper forms the general problem of incentive mechanism design for ROI-constrained auto-bidding, and carries out analysis of strategy-proof requirements for the revenue-maximizing and profit-maximize advertisers and provides a mechanism framework and a practical solution to guarantee the incentive property for different types of advertisers.
JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu
TLDR
This work presents JIZHI - a Model-as-a-Service system that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.
The Role of Pragmatic Strategies on University Campaign
This paper aims to provide information that pragmatic strategies is needed to offer university campaign and branding. Researcher used Aristotle’s argumentation, ethos, logos and pathos to gain target

References

SHOWING 1-10 OF 53 REFERENCES
Automatic generation of bid phrases for online advertising
TLDR
Empirical evaluation based on a real-life corpus of advertiser-created landing pages and associated bid phrases confirms the value of the approach, which successfully re-generates many of the human-crafted bid phrases and performs significantly better than a pure text extraction method.
Search advertising using web relevance feedback
TLDR
Empirical evaluation based on over 9,000 query-ad pairwise judgments confirms that using augmented queries produces highly relevant ads.
Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising
TLDR
This study presents a novel advance match approach based on the idea of semantic embeddings of queries and ads that significantly outperforms baselines in terms of relevance, coverage and incremental revenue.
Bid generation for advanced match in sponsored search
TLDR
This work proposes a statistical approach to solve the bid generation problem and examines two information sources: the bidding behavior of advertisers, and the conversion data, suggesting that sophisticated advertisers' bids are driven by many factors beyond clicks and immediate measurable conversions.
Estimating advertisability of tail queries for sponsored search
TLDR
A simple, yet effective, approach, which estimates query advertisability for infrequent or "tail" queries using only the words present in the queries is given, which outperforms a more complex approach based on regularized regression.
Bid keyword suggestion in sponsored search based on competitiveness and relevance
Algorithmic Methods for Sponsored Search Advertising
TLDR
An overview of the current systems for such auctions for sponsored search advertising is presented and the underlying game-theoretic aspects of the algorithms for bidding and pricing use techniques from three mathematical areas: mechanism design, optimization, and statistical estimation.
Beyond Keywords and Relevance: A Personalized Ad Retrieval Framework in E-Commerce Sponsored Search
TLDR
A novel ad retrieval framework beyond keywords and relevance in e-commerce sponsored search is proposed, in which personalized information is introduced and a model on top of the hierarchical network representing signals, keys and ads is trained.
Catching the drift: learning broad matches from clickthrough data
TLDR
An online learning algorithm, Amnesiac Averaged Perceptron, that is highly efficient yet able to quickly adjust to the rapidly-changing distributions of bidded keywords, advertisements and user behavior is presented.
Optimized Cost per Click in Taobao Display Advertising
TLDR
A bid optimizing strategy called optimized cost per click (OCPC) is proposed which automatically adjusts the bid to achieve finer matching of bid and traffic quality of page view (PV) request granularity and yields substantially better results than previous fixed bid manner.
...
...