Predicting bidders' willingness to pay in online multiunit ascending auctions: Analytical and empirical insights

Ravi Bapna, Paulo B Goes, Alok Gupta, Gilbert Karuga

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

we develop a real-time estimation approach to predict bidders' maximum willingness to pay in a multiunit ascending uniform-price and discriminatory-price (Yankee) online auction. Our two-stage approach begins with a bidder classification step, which is followed by an analytical prediction model. The classification model identifies bidders as either adopting a myopic best-response (MBR) bidding strategy or a non-MBR strategy. We then use a generalized bid-inversion function to estimate the willingness to pay for MBR bidders. We empirically validate our two-stage approach using data from two popular online auction sites. Our joint classification-and- prediction approach outperforms two other naive prediction strategies that draw random valuations between a bidder's current bid and the known market upper bound. Our prediction results indicate that, on average, our estimates are within 2% of bidders' revealed willingness to pay for Yankee and uniform-price multiunit auctions. We discuss how our results can facilitate mechanism-design changes such as dynamic-bid increments and dynamic buy-it-now prices.

Original languageEnglish (US)
Pages (from-to)345-355
Number of pages11
JournalINFORMS Journal on Computing
Volume20
Issue number3
DOIs
StatePublished - Jun 2008
Externally publishedYes

Fingerprint

Willingness-to-pay
Ascending auctions
Prediction
Bid
Best response
Uniform price
Online auctions
Mechanism design
Prediction model
Bidding strategy
Upper bound
Multi-unit auctions

Keywords

  • Dynamic-mechanism design
  • Online auctions
  • Predicting willingness to pay

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Computer Science Applications
  • Management Science and Operations Research

Cite this

Predicting bidders' willingness to pay in online multiunit ascending auctions : Analytical and empirical insights. / Bapna, Ravi; Goes, Paulo B; Gupta, Alok; Karuga, Gilbert.

In: INFORMS Journal on Computing, Vol. 20, No. 3, 06.2008, p. 345-355.

Research output: Contribution to journalArticle

@article{f207d5bd031444e7971f3b3e5f17d8d6,
title = "Predicting bidders' willingness to pay in online multiunit ascending auctions: Analytical and empirical insights",
abstract = "we develop a real-time estimation approach to predict bidders' maximum willingness to pay in a multiunit ascending uniform-price and discriminatory-price (Yankee) online auction. Our two-stage approach begins with a bidder classification step, which is followed by an analytical prediction model. The classification model identifies bidders as either adopting a myopic best-response (MBR) bidding strategy or a non-MBR strategy. We then use a generalized bid-inversion function to estimate the willingness to pay for MBR bidders. We empirically validate our two-stage approach using data from two popular online auction sites. Our joint classification-and- prediction approach outperforms two other naive prediction strategies that draw random valuations between a bidder's current bid and the known market upper bound. Our prediction results indicate that, on average, our estimates are within 2{\%} of bidders' revealed willingness to pay for Yankee and uniform-price multiunit auctions. We discuss how our results can facilitate mechanism-design changes such as dynamic-bid increments and dynamic buy-it-now prices.",
keywords = "Dynamic-mechanism design, Online auctions, Predicting willingness to pay",
author = "Ravi Bapna and Goes, {Paulo B} and Alok Gupta and Gilbert Karuga",
year = "2008",
month = "6",
doi = "10.1287/ijoc.l070.0247",
language = "English (US)",
volume = "20",
pages = "345--355",
journal = "INFORMS Journal on Computing",
issn = "1091-9856",
publisher = "INFORMS Inst.for Operations Res.and the Management Sciences",
number = "3",

}

TY - JOUR

T1 - Predicting bidders' willingness to pay in online multiunit ascending auctions

T2 - Analytical and empirical insights

AU - Bapna, Ravi

AU - Goes, Paulo B

AU - Gupta, Alok

AU - Karuga, Gilbert

PY - 2008/6

Y1 - 2008/6

N2 - we develop a real-time estimation approach to predict bidders' maximum willingness to pay in a multiunit ascending uniform-price and discriminatory-price (Yankee) online auction. Our two-stage approach begins with a bidder classification step, which is followed by an analytical prediction model. The classification model identifies bidders as either adopting a myopic best-response (MBR) bidding strategy or a non-MBR strategy. We then use a generalized bid-inversion function to estimate the willingness to pay for MBR bidders. We empirically validate our two-stage approach using data from two popular online auction sites. Our joint classification-and- prediction approach outperforms two other naive prediction strategies that draw random valuations between a bidder's current bid and the known market upper bound. Our prediction results indicate that, on average, our estimates are within 2% of bidders' revealed willingness to pay for Yankee and uniform-price multiunit auctions. We discuss how our results can facilitate mechanism-design changes such as dynamic-bid increments and dynamic buy-it-now prices.

AB - we develop a real-time estimation approach to predict bidders' maximum willingness to pay in a multiunit ascending uniform-price and discriminatory-price (Yankee) online auction. Our two-stage approach begins with a bidder classification step, which is followed by an analytical prediction model. The classification model identifies bidders as either adopting a myopic best-response (MBR) bidding strategy or a non-MBR strategy. We then use a generalized bid-inversion function to estimate the willingness to pay for MBR bidders. We empirically validate our two-stage approach using data from two popular online auction sites. Our joint classification-and- prediction approach outperforms two other naive prediction strategies that draw random valuations between a bidder's current bid and the known market upper bound. Our prediction results indicate that, on average, our estimates are within 2% of bidders' revealed willingness to pay for Yankee and uniform-price multiunit auctions. We discuss how our results can facilitate mechanism-design changes such as dynamic-bid increments and dynamic buy-it-now prices.

KW - Dynamic-mechanism design

KW - Online auctions

KW - Predicting willingness to pay

UR - http://www.scopus.com/inward/record.url?scp=61349199461&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61349199461&partnerID=8YFLogxK

U2 - 10.1287/ijoc.l070.0247

DO - 10.1287/ijoc.l070.0247

M3 - Article

AN - SCOPUS:61349199461

VL - 20

SP - 345

EP - 355

JO - INFORMS Journal on Computing

JF - INFORMS Journal on Computing

SN - 1091-9856

IS - 3

ER -