A PSO-based algorithm for reserve price optimization in online ad auctions

Jason Rhuggenaath; Alp Akcay; Yingqian Zhang; Uzay Kaymak

doi:10.1109/CEC.2019.8789915

A PSO-based algorithm for reserve price optimization in online ad auctions

Jason Rhuggenaath, Alp Akcay, Yingqian Zhang, Uzay Kaymak

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

138 Downloads (Pure)

Abstract

One of the main mechanisms that online publishers use in online advertising in order to sell their advertisement space is the real-time bidding (RTB) mechanism. In RTB the publisher sells advertisement space via a second-price auction. Publishers can set a reserve price for their inventory in the second-price auction. In this paper we consider an online publisher that sells advertisement space and propose a method for learning optimal reserve prices in second-price auctions. We study a limited information setting where the values of the bids are not revealed and no historical information about the values of the bids is available. Our proposed method leverages the dynamics of particles in particle swarm optimization (PSO) to set reserve prices and is suitable for non-stationary environments. We also show that, taking the gap between the winning bid and second highest bid into account leads to better decisions for the reserve prices. Experiments using real-life ad auction data show that the proposed method outperforms popular bandit algorithms.

Original language	English
Title of host publication	2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	2611-2619
Number of pages	9
ISBN (Electronic)	9781728121536
DOIs	https://doi.org/10.1109/CEC.2019.8789915
Publication status	Published - Jun 2019
Event	2019 IEEE Congress on Evolutionary Computation - Wellington, New Zealand Duration: 10 Jun 2019 → 13 Jun 2019 http://cec2019.org/

Conference

Conference	2019 IEEE Congress on Evolutionary Computation
Country	New Zealand
City	Wellington
Period	10/06/19 → 13/06/19
Internet address	http://cec2019.org/

Access to Document

10.1109/CEC.2019.8789915

Authors versionFinal author version , 319 KB

Link to publication in Scopus

Fingerprint Dive into the research topics of 'A PSO-based algorithm for reserve price optimization in online ad auctions'. Together they form a unique fingerprint.

Cite this

Rhuggenaath, J., Akcay, A., Zhang, Y., & Kaymak, U. (2019). A PSO-based algorithm for reserve price optimization in online ad auctions. In 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings (pp. 2611-2619). [8789915] Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CEC.2019.8789915

@inproceedings{84e275765e7740d5ada7da7ceec3a914,

title = "A PSO-based algorithm for reserve price optimization in online ad auctions",

abstract = "One of the main mechanisms that online publishers use in online advertising in order to sell their advertisement space is the real-time bidding (RTB) mechanism. In RTB the publisher sells advertisement space via a second-price auction. Publishers can set a reserve price for their inventory in the second-price auction. In this paper we consider an online publisher that sells advertisement space and propose a method for learning optimal reserve prices in second-price auctions. We study a limited information setting where the values of the bids are not revealed and no historical information about the values of the bids is available. Our proposed method leverages the dynamics of particles in particle swarm optimization (PSO) to set reserve prices and is suitable for non-stationary environments. We also show that, taking the gap between the winning bid and second highest bid into account leads to better decisions for the reserve prices. Experiments using real-life ad auction data show that the proposed method outperforms popular bandit algorithms.",

author = "Jason Rhuggenaath and Alp Akcay and Yingqian Zhang and Uzay Kaymak",

year = "2019",

month = "6",

doi = "10.1109/CEC.2019.8789915",

language = "English",

pages = "2611--2619",

booktitle = "2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Rhuggenaath, J , Akcay, A , Zhang, Y & Kaymak, U 2019, A PSO-based algorithm for reserve price optimization in online ad auctions. in 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings., 8789915, Institute of Electrical and Electronics Engineers, Piscataway, pp. 2611-2619, 2019 IEEE Congress on Evolutionary Computation, Wellington, New Zealand, 10/06/19. https://doi.org/10.1109/CEC.2019.8789915

A PSO-based algorithm for reserve price optimization in online ad auctions. / Rhuggenaath, Jason ; Akcay, Alp ; Zhang, Yingqian ; Kaymak, Uzay.

2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Piscataway : Institute of Electrical and Electronics Engineers, 2019. p. 2611-2619 8789915.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A PSO-based algorithm for reserve price optimization in online ad auctions

AU - Rhuggenaath, Jason

AU - Akcay, Alp

AU - Zhang, Yingqian

AU - Kaymak, Uzay

PY - 2019/6

Y1 - 2019/6

N2 - One of the main mechanisms that online publishers use in online advertising in order to sell their advertisement space is the real-time bidding (RTB) mechanism. In RTB the publisher sells advertisement space via a second-price auction. Publishers can set a reserve price for their inventory in the second-price auction. In this paper we consider an online publisher that sells advertisement space and propose a method for learning optimal reserve prices in second-price auctions. We study a limited information setting where the values of the bids are not revealed and no historical information about the values of the bids is available. Our proposed method leverages the dynamics of particles in particle swarm optimization (PSO) to set reserve prices and is suitable for non-stationary environments. We also show that, taking the gap between the winning bid and second highest bid into account leads to better decisions for the reserve prices. Experiments using real-life ad auction data show that the proposed method outperforms popular bandit algorithms.

AB - One of the main mechanisms that online publishers use in online advertising in order to sell their advertisement space is the real-time bidding (RTB) mechanism. In RTB the publisher sells advertisement space via a second-price auction. Publishers can set a reserve price for their inventory in the second-price auction. In this paper we consider an online publisher that sells advertisement space and propose a method for learning optimal reserve prices in second-price auctions. We study a limited information setting where the values of the bids are not revealed and no historical information about the values of the bids is available. Our proposed method leverages the dynamics of particles in particle swarm optimization (PSO) to set reserve prices and is suitable for non-stationary environments. We also show that, taking the gap between the winning bid and second highest bid into account leads to better decisions for the reserve prices. Experiments using real-life ad auction data show that the proposed method outperforms popular bandit algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85069519168&partnerID=8YFLogxK

U2 - 10.1109/CEC.2019.8789915

DO - 10.1109/CEC.2019.8789915

M3 - Conference contribution

SP - 2611

EP - 2619

BT - 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -