A reinforcement learning method to select ad networks in Waterfall Strategy

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

A high percentage of online advertising is currently performed through real time bidding. Impressions are generated once a user visits the websites containing empty ad slots, which are subsequently sold in an online ad exchange market. Nowadays, one of the most important sources of income for publishers who own websites is through online advertising. From a publisher’s point of view it is critical to send its impressions to most profitable ad networks and to fill its ad slots quickly in order to increase their revenue. In this paper we present a method for helping publishers to decide which ad networks to use for each available impression. Our proposed method uses reinforcement learning with initial state-action values obtained from a prediction model to find the best ordering of ad networks in the waterfall fashion. We show that this method increases the expected revenue of the publisher.
LanguageEnglish
Title of host publicationICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2
EditorsLuc Steels, Ana Rocha, Jaap van den Herik
PublisherSCITEPRESS-Science and Technology Publications, Lda.
Pages265-265
Number of pages10
ISBN (Electronic)9789897583506
ISBN (Print)978-989-758-350-6
DOIs
StatePublished - 2019
Event11th International Conference on Agents and Artificial Intelligence, ICAART 2019 - Prague, Czech Republic
Duration: 19 Feb 201921 Feb 2019
http://www.icaart.org/

Conference

Conference11th International Conference on Agents and Artificial Intelligence, ICAART 2019
Abbreviated titleICAART2019
CountryCzech Republic
CityPrague
Period19/02/1921/02/19
Internet address

Fingerprint

Reinforcement learning
Websites
Marketing

Keywords

  • Ad Network
  • Online AD Auction
  • Predictive Model
  • Real Time Bidding
  • Reinforcement Learning
  • Supply Side Platform

Cite this

Refaei Afshar, R., Zhang, Y., Firat, M., & Kaymak, U. (2019). A reinforcement learning method to select ad networks in Waterfall Strategy. In L. Steels, A. Rocha, & J. van den Herik (Eds.), ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2 (pp. 265-265). SCITEPRESS-Science and Technology Publications, Lda.. DOI: 10.5220/0007395502560265
Refaei Afshar, R. ; Zhang, Y. ; Firat, M. ; Kaymak, U./ A reinforcement learning method to select ad networks in Waterfall Strategy. ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2. editor / Luc Steels ; Ana Rocha ; Jaap van den Herik. SCITEPRESS-Science and Technology Publications, Lda., 2019. pp. 265-265
@inproceedings{54b4096dce5e400ba60ad68c2b5a9275,
title = "A reinforcement learning method to select ad networks in Waterfall Strategy",
abstract = "A high percentage of online advertising is currently performed through real time bidding. Impressions are generated once a user visits the websites containing empty ad slots, which are subsequently sold in an online ad exchange market. Nowadays, one of the most important sources of income for publishers who own websites is through online advertising. From a publisher’s point of view it is critical to send its impressions to most profitable ad networks and to fill its ad slots quickly in order to increase their revenue. In this paper we present a method for helping publishers to decide which ad networks to use for each available impression. Our proposed method uses reinforcement learning with initial state-action values obtained from a prediction model to find the best ordering of ad networks in the waterfall fashion. We show that this method increases the expected revenue of the publisher.",
keywords = "Ad Network, Online AD Auction, Predictive Model, Real Time Bidding, Reinforcement Learning, Supply Side Platform",
author = "{Refaei Afshar}, R. and Y. Zhang and M. Firat and U. Kaymak",
year = "2019",
doi = "10.5220/0007395502560265",
language = "English",
isbn = "978-989-758-350-6",
pages = "265--265",
editor = "Luc Steels and Ana Rocha and {van den Herik}, Jaap",
booktitle = "ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2",
publisher = "SCITEPRESS-Science and Technology Publications, Lda.",

}

Refaei Afshar, R, Zhang, Y, Firat, M & Kaymak, U 2019, A reinforcement learning method to select ad networks in Waterfall Strategy. in L Steels, A Rocha & J van den Herik (eds), ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2. SCITEPRESS-Science and Technology Publications, Lda., pp. 265-265, 11th International Conference on Agents and Artificial Intelligence, ICAART 2019, Prague, Czech Republic, 19/02/19. DOI: 10.5220/0007395502560265

A reinforcement learning method to select ad networks in Waterfall Strategy. / Refaei Afshar, R.; Zhang, Y.; Firat, M.; Kaymak, U.

ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2. ed. / Luc Steels; Ana Rocha; Jaap van den Herik. SCITEPRESS-Science and Technology Publications, Lda., 2019. p. 265-265.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - A reinforcement learning method to select ad networks in Waterfall Strategy

AU - Refaei Afshar,R.

AU - Zhang,Y.

AU - Firat,M.

AU - Kaymak,U.

PY - 2019

Y1 - 2019

N2 - A high percentage of online advertising is currently performed through real time bidding. Impressions are generated once a user visits the websites containing empty ad slots, which are subsequently sold in an online ad exchange market. Nowadays, one of the most important sources of income for publishers who own websites is through online advertising. From a publisher’s point of view it is critical to send its impressions to most profitable ad networks and to fill its ad slots quickly in order to increase their revenue. In this paper we present a method for helping publishers to decide which ad networks to use for each available impression. Our proposed method uses reinforcement learning with initial state-action values obtained from a prediction model to find the best ordering of ad networks in the waterfall fashion. We show that this method increases the expected revenue of the publisher.

AB - A high percentage of online advertising is currently performed through real time bidding. Impressions are generated once a user visits the websites containing empty ad slots, which are subsequently sold in an online ad exchange market. Nowadays, one of the most important sources of income for publishers who own websites is through online advertising. From a publisher’s point of view it is critical to send its impressions to most profitable ad networks and to fill its ad slots quickly in order to increase their revenue. In this paper we present a method for helping publishers to decide which ad networks to use for each available impression. Our proposed method uses reinforcement learning with initial state-action values obtained from a prediction model to find the best ordering of ad networks in the waterfall fashion. We show that this method increases the expected revenue of the publisher.

KW - Ad Network

KW - Online AD Auction

KW - Predictive Model

KW - Real Time Bidding

KW - Reinforcement Learning

KW - Supply Side Platform

UR - http://www.scopus.com/inward/record.url?scp=85064820139&partnerID=8YFLogxK

U2 - 10.5220/0007395502560265

DO - 10.5220/0007395502560265

M3 - Conference contribution

SN - 978-989-758-350-6

SP - 265

EP - 265

BT - ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2

PB - SCITEPRESS-Science and Technology Publications, Lda.

ER -

Refaei Afshar R, Zhang Y, Firat M, Kaymak U. A reinforcement learning method to select ad networks in Waterfall Strategy. In Steels L, Rocha A, van den Herik J, editors, ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence: volume 2. SCITEPRESS-Science and Technology Publications, Lda.2019. p. 265-265. Available from, DOI: 10.5220/0007395502560265