A reinforcement learning method to select ad networks in Waterfall Strategy

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

3 Citaties (Scopus)

Uittreksel

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.
TaalEngels
TitelICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence
RedacteurenLuc Steels, Ana Rocha, Jaap van den Herik
UitgeverijSCITEPRESS-Science and Technology Publications, Lda.
Pagina's256-265
Aantal pagina's10
Volume2
ISBN van elektronische versie9789897583506
ISBN van geprinte versie978-989-758-350-6
DOI's
StatusGepubliceerd - 2019
Evenement11th International Conference on Agents and Artificial Intelligence, ICAART 2019 - Prague, Tsjechië
Duur: 19 feb 201921 feb 2019
http://www.icaart.org/

Congres

Congres11th International Conference on Agents and Artificial Intelligence, ICAART 2019
Verkorte titelICAART2019
LandTsjechië
StadPrague
Periode19/02/1921/02/19
Internet adres

Vingerafdruk

Reinforcement learning
Websites
Marketing

Trefwoorden

    Citeer dit

    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 (editors), ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence (Vol. 2, blz. 256-265). 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. redacteur / Luc Steels ; Ana Rocha ; Jaap van den Herik. Vol. 2 SCITEPRESS-Science and Technology Publications, Lda., 2019. blz. 256-265
    @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",
    volume = "2",
    pages = "256--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",
    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 (redactie), ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. vol. 2, SCITEPRESS-Science and Technology Publications, Lda., blz. 256-265, Prague, Tsjechië, 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. redactie / Luc Steels; Ana Rocha; Jaap van den Herik. Vol. 2 SCITEPRESS-Science and Technology Publications, Lda., 2019. blz. 256-265.

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer 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

    VL - 2

    SP - 256

    EP - 265

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

    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, redacteurs, ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. Vol. 2. SCITEPRESS-Science and Technology Publications, Lda.2019. blz. 256-265. Beschikbaar vanaf, DOI: 10.5220/0007395502560265