Optimal Allocation of Real-Time-Bidding and Direct Campaigns

Jauvion, Grégoire; Grislain, Nicolas

doi:10.1145/3219819.3219877

Cited by 11 publications

(9 citation statements)

References 15 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second topic most discussed in our survey in relation to the campaign setting is the proposal of different algorithms to optimize viewability and other KPIs (such as engagement or video completion) in video ad campaigns to improve brand recognition and ROI [24,60,77,81,120]. Viewability could also be optimized in the campaign creation by selecting those ad formats that are more likely to be viewed.…”

Section: ) Campaign Settingsmentioning

confidence: 99%

A Survey of the Role of Viewability Within the Online Advertising Ecosystem

et al. 2021

View full text Add to dashboard Cite

We also want to thank ExoClick for their support in conducting this research. The project that gave rise to these results received the support of a fellowship from "la Caixa" Foundation (ID 100010434) and from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 847648. The fellowship code is LCF/BQ/PR20/11770009. We also acknowledge support from the Spanish Ministry of Economy and Competitiveness through the Juan de la Cierva Formación program (FJCI-2017-34926) ABSTRACT Within the online advertising ecosystem, viewability is defined as the metric that measures if an ad impression had the chance of being viewable by a potential consumer. Although this metric has been presented as a potential game-changer within the ad industry, it has not been fully adopted by the stakeholders, mainly due to disagreement between the different parties on the standards to implement and measure it, and its potential benefits and drawbacks. In this study, we present a survey of the role that viewability can have on the main challenges of the online advertising ecosystem depicting the main applications, benefits and issues. With this objective, we provide an overall picture of how viewability can fit within the ecosystem, which can help the different stakeholders to work on its adoption, integration and establishing a research agenda.

show abstract

Section: ) Campaign Settingsmentioning

confidence: 99%

A Survey of the Role of Viewability Within the Online Advertising Ecosystem

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[Chen et al 2011] solves a bidding problem with multiple campaigns and from the perspective of the publisher using linear programming and duality. A similar question is solved in [Balseiro et al 2014;Jauvion and Grislain 2018]. In those papers, the publisher wants to allocate impressions to campaigns in competition with third party RTB campaigns.…”

Section: Related Papersmentioning

confidence: 99%

“…In those papers, the publisher wants to allocate impressions to campaigns in competition with third party RTB campaigns. [Jauvion and Grislain 2018] allows for underdelivery by introducing a penalty for underdelivery in its optimization program. [Ghosh et al 2009] describes a solution to the bidding problem with budget constraints and partially observed exchange.…”

Section: Related Papersmentioning

confidence: 99%

Recurrent Neural Networks for Stochastic Control in Real-Time Bidding

Grislain¹,

Perrin²,

Thabault³

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

View full text Add to dashboard Cite

Bidding in real-time auctions can be a difficult stochastic control task; especially if underdelivery incurs strong penalties and the market is very uncertain.Most current works and implementations focus on optimally delivering a campaign given a reasonable forecast of the market. Practical implementations have a feedback loop to adjust and be robust to forecasting errors, but no implementation, to the best of our knowledge, uses a model of market risk and actively anticipates market shifts.Solving such stochastic control problems in practice is actually very challenging. This paper proposes an approximate solution based on a Recurrent Neural Network (RNN) architecture that is both effective and practical for implementation in a production environment. The RNN bidder provisions everything it needs to avoid missing its goal. It also deliberately falls short of its goal when buying the missing impressions would cost more than the penalty for not reaching it.

show abstract

“…Balseiro et al (2014) proposed learning a stochastic policy to maximize the yield of a publisher based on the contract first strategy, which has been proved not optimal in our experimental evaluations. Recently, a new strategy maximizing the total revenue was proposed in (Jauvion and Grislain, 2018). However, the challenge of environment instability was not discussed or addressed.…”

Section: Related Workmentioning

confidence: 99%

“…What makes it even more challenging is the instability of the environment. When deriving the optimal impression allocation strategy, the stationary assumptions presented in the work by (Li et al, 2016;Jauvion and Grislain, 2018;Balseiro et al, 2014) are difficult to satisfy in the real-world scenarios. First, the environment stability is vulnerable to unexpected traffic changes such as those brought by sales events on holidays.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising

Wu,

Chen,

Yang

et al. 2018

Preprint

View full text Add to dashboard Cite

In online display advertising, guaranteed contracts and real-time bidding (RTB) are two major ways to sell impressions for a publisher. Despite the increasing popularity of RTB, there is still half of online display advertising revenue generated from guaranteed contracts. Therefore, simultaneously selling impressions through both guaranteed contracts and RTB is a straightforward choice for a publisher to maximize its yield. However, deriving the optimal strategy to allocate impressions is not a trivial task, especially when the environment is unstable in real-world applications. In this paper, we formulate the impression allocation problem as an auction problem where each contract can submit virtual bids for individual impressions. With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts. Since the bids from contracts are decided by the publisher, we propose a multi-agent reinforcement learning (MARL) approach to derive cooperative policies for the publisher to maximize its yield in an unstable environment. The proposed approach also resolves the common challenges in MARL such as input dimension explosion, reward credit assignment, and non-stationary environment. Experimental evaluations on large-scale real datasets demonstrate the effectiveness of our approach.

show abstract

Optimal Allocation of Real-Time-Bidding and Direct Campaigns

Cited by 11 publications

References 15 publications

A Survey of the Role of Viewability Within the Online Advertising Ecosystem

A Survey of the Role of Viewability Within the Online Advertising Ecosystem

Recurrent Neural Networks for Stochastic Control in Real-Time Bidding

A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising

Contact Info

Product

Resources

About