Reserve price optimization with header bidding and Ad Exchange

Afshar, Reza Refaei; Zhang, Yingqian; Fırat, Murat; Kaymak, Uzay; Metin, Ali Izzet; Tarakcioglu, Gonenc Secil; Bas, Cosku

doi:10.1109/smc42975.2020.9283479

Cited by 3 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The failure rate of reserve price in HB and AdX systems is studied in [25] using survival analysis. The idea of survival analysis is extended in [5] to increase the reserve price. In [26], the focus is on optimizing the revenue of AdX.…”

Section: Related Workmentioning

confidence: 99%

“…Due to GDPR 1 , user data are not used in our method. The aforementioned information and ζ HBP t constitute the state s t for impression t as shown in (5).…”

Section: B State and Action Definitionmentioning

confidence: 99%

“…As mentioned before, AdX provides no information about ζ AdX t while this value is crucial for determining whether a reserve price is outbid. We use RTB historical data that contains the information shown in (5) for four randomly selected features sets are shown in Fig. 3.…”

Section: Rtb Simulatormentioning

confidence: 99%

“…Besides, the process of adjusting the reserve price can be considered as a sequential decision making task in a possibly infinite horizon where in each decision moment, an impression is generated and a reserve price is determined. In addition, as shown in [5], the bid values of HBPs and also the winner bid of AdX would not be predicted well without any information about the end users and advertisers. These reasons make the problem suitable for Reinforcement Learning (RL).…”

Section: Introductionmentioning

confidence: 96%

“…Then, a reserve price is set according to the HBPs bids and another ad request is sent to an AdX. If AdX's winner bid is higher than the highest bid of HBPs, the impression goes to AdX winner, otherwise, it goes to the HBP winner [5].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning

Afshar

Rhuggenaath

Zhang

et al. 2021

2021 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User

show abstract

Section: Related Workmentioning

confidence: 99%

“…Due to GDPR 1 , user data are not used in our method. The aforementioned information and ζ HBP t constitute the state s t for impression t as shown in (5).…”

Section: B State and Action Definitionmentioning

confidence: 99%

Section: Rtb Simulatormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning

Afshar

Rhuggenaath

Zhang

et al. 2021

2021 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

Dynamic Ad Network Ordering Method Using Reinforcement Learning

Afshar

Zhang

Kaymak

2022

Int J Comput Intell Syst

Self Cite

View full text Add to dashboard Cite

Real time bidding is one of the most popular ways of selling impressions in online advertising, where online ad publishers allocate some blocks in their websites to sell in online auctions. In real time bidding, ad networks connect publishers and advertisers. There are many available ad networks for publishers to choose from. A possible approach for selecting ad networks and sending ad requests is called Waterfall Strategy, in which ad networks are selected sequentially. The ordering of the ad networks is very important for publishers, and finding the ordering that will provide maximum revenue is a hard problem due to the highly dynamic environment. In this paper, we propose a dynamic ad network ordering method to find the best ordering of ad networks for publishers that opt for Waterfall Strategy to select ad networks. This method consists of two steps. The first step is a prediction model that is trained on real time bidding historical data and provides an estimation of revenue for each impression. These estimations are used as initial values for the Q-table in the second step. The second step is based on Reinforcement Learning and improves the output of the prediction model. By calculating the revenue of our method and comparing that with the revenue of a fixed and predefined ordering method, we show that our proposed dynamic ad network ordering method increases publishers’ revenue.

show abstract