A decision support method to increase the revenue of ad publishers in waterfall strategy

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

4 Citaties (Scopus)
46 Downloads (Pure)

Uittreksel

Online advertising is one of the most important sources of income for many online publishers. The process is as easy as placing slots in the website and selling those slots in real time bidding auctions. Since websites load in few milliseconds, the bidding and selling process should not take too much time. Sellers or publishers of advertisements tend to maximize the revenue obtained through online advertising. Recently, we proposed a method to select the most profitable ad network for each ad request. Our method consists of two parts: a prediction model and a reinforcement learning modeling. In this paper we evaluate the prediction model and test two methods of ad network ordering. First we use prediction model and second the two-step method. We show that the ad network ordering obtained from the second step of our method increases the revenue and the prediction model provides initial values which could not be used as a decision method.
Originele taal-2Engels
TitelCIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's8
ISBN van elektronische versie9781728100333
DOI's
StatusGepubliceerd - 1 mei 2019
Evenement2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, (CIFEr2019) - Shenzhen, China
Duur: 4 mei 20195 mei 2019
http://www.ieee-cifer.org/website_cifer/about_2019.html

Congres

Congres2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, (CIFEr2019)
Verkorte titelCIFEr2019
LandChina
StadShenzhen
Periode4/05/195/05/19
Internet adres

Vingerafdruk

Websites
Marketing
Sales
Reinforcement learning

Citeer dit

Refaei Afshar, R., Zhang, Y., Firat, M., & Kaymak, U. (2019). A decision support method to increase the revenue of ad publishers in waterfall strategy. In CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics [8759106] Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CIFEr.2019.8759106
Refaei Afshar, Reza ; Zhang, Yingqian ; Firat, Murat ; Kaymak, Uzay. / A decision support method to increase the revenue of ad publishers in waterfall strategy. CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics. Piscataway : Institute of Electrical and Electronics Engineers, 2019.
@inproceedings{f9c000df2bf74b0cab54f51193a85633,
title = "A decision support method to increase the revenue of ad publishers in waterfall strategy",
abstract = "Online advertising is one of the most important sources of income for many online publishers. The process is as easy as placing slots in the website and selling those slots in real time bidding auctions. Since websites load in few milliseconds, the bidding and selling process should not take too much time. Sellers or publishers of advertisements tend to maximize the revenue obtained through online advertising. Recently, we proposed a method to select the most profitable ad network for each ad request. Our method consists of two parts: a prediction model and a reinforcement learning modeling. In this paper we evaluate the prediction model and test two methods of ad network ordering. First we use prediction model and second the two-step method. We show that the ad network ordering obtained from the second step of our method increases the revenue and the prediction model provides initial values which could not be used as a decision method.",
keywords = "ad networks, Predictive model, Real time bidding, Reinforcement Learning",
author = "{Refaei Afshar}, Reza and Yingqian Zhang and Murat Firat and Uzay Kaymak",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/CIFEr.2019.8759106",
language = "English",
booktitle = "CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Refaei Afshar, R, Zhang, Y, Firat, M & Kaymak, U 2019, A decision support method to increase the revenue of ad publishers in waterfall strategy. in CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics., 8759106, Institute of Electrical and Electronics Engineers, Piscataway, 2019 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, (CIFEr2019), Shenzhen, China, 4/05/19. https://doi.org/10.1109/CIFEr.2019.8759106

A decision support method to increase the revenue of ad publishers in waterfall strategy. / Refaei Afshar, Reza; Zhang, Yingqian; Firat, Murat; Kaymak, Uzay.

CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics. Piscataway : Institute of Electrical and Electronics Engineers, 2019. 8759106.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

TY - GEN

T1 - A decision support method to increase the revenue of ad publishers in waterfall strategy

AU - Refaei Afshar, Reza

AU - Zhang, Yingqian

AU - Firat, Murat

AU - Kaymak, Uzay

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Online advertising is one of the most important sources of income for many online publishers. The process is as easy as placing slots in the website and selling those slots in real time bidding auctions. Since websites load in few milliseconds, the bidding and selling process should not take too much time. Sellers or publishers of advertisements tend to maximize the revenue obtained through online advertising. Recently, we proposed a method to select the most profitable ad network for each ad request. Our method consists of two parts: a prediction model and a reinforcement learning modeling. In this paper we evaluate the prediction model and test two methods of ad network ordering. First we use prediction model and second the two-step method. We show that the ad network ordering obtained from the second step of our method increases the revenue and the prediction model provides initial values which could not be used as a decision method.

AB - Online advertising is one of the most important sources of income for many online publishers. The process is as easy as placing slots in the website and selling those slots in real time bidding auctions. Since websites load in few milliseconds, the bidding and selling process should not take too much time. Sellers or publishers of advertisements tend to maximize the revenue obtained through online advertising. Recently, we proposed a method to select the most profitable ad network for each ad request. Our method consists of two parts: a prediction model and a reinforcement learning modeling. In this paper we evaluate the prediction model and test two methods of ad network ordering. First we use prediction model and second the two-step method. We show that the ad network ordering obtained from the second step of our method increases the revenue and the prediction model provides initial values which could not be used as a decision method.

KW - ad networks

KW - Predictive model

KW - Real time bidding

KW - Reinforcement Learning

UR - http://www.scopus.com/inward/record.url?scp=85069511307&partnerID=8YFLogxK

U2 - 10.1109/CIFEr.2019.8759106

DO - 10.1109/CIFEr.2019.8759106

M3 - Conference contribution

AN - SCOPUS:85069511307

BT - CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Refaei Afshar R, Zhang Y, Firat M, Kaymak U. A decision support method to increase the revenue of ad publishers in waterfall strategy. In CIFEr 2019 - IEEE Conference on Computational Intelligence for Financial Engineering and Economics. Piscataway: Institute of Electrical and Electronics Engineers. 2019. 8759106 https://doi.org/10.1109/CIFEr.2019.8759106