US 7,627,514 B2Granted

Method and system for selecting an optimal auction format

AssigneeHewlett-Packard Development Company, L.P.

InventorsKemal Guler, Tongwei Liu, Hsiu-Khuern Tang

Life of this patent

Estimating the term…

Loading patent…

Abstract

An automated estimation and optimization solution for selecting the best auction format by determining the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements. Structural analysis of bid data from prior auctions is used to identify and estimate the distributions of bidders' private signals conditional on observable bidder characteristics. The estimated signal distributions, identified by the structural analysis, are used to evaluate alternative auction formats and to select the best format from among a given set of candidates. The present invention provides decision support tools to select an auction format based on structural econometric analysis of available data on the market environment. A decision-maker may estimate the unobservable private signals of the bidders and to determine the best auction format the decision maker can employ to sell a given set of items.

Claims24

Dependent claims

A method for determining an auction format for a market, said method comprising the steps of:

selecting, performed by a computer system, characteristics of said market based at least in part on stored historical bids data that includes data for historical auctions performed in the past for a plurality of bidders, wherein said historical bids data is stored on computer readable medium that is accessed by said computer system;
selecting, performed by said computer system, a relevant bidding model that specifies past bidding behavior as a function of information held privately by a bidder, that is determined based at least in part on said historical auctions data, and said characteristics of said market based on segments of said historical auctions related to a specified item;
selecting, performed by said computer system, at least a first estimated structure of said market, which describes at least a first factor that affects how bidders behave, and a second estimated structure of said market, which describes a second factor that affects how bidders behave, at least in part by inverting said relevant bidding model;
predicting, performed by said computer system, a first bidding behavior utilizing said first estimated structure of said market, said characteristics of said market and said relevant bidding model;
predicting, performed by said computer system, a first outcome of said market based on said first bidding behavior;
predicting, performed by said computer system, at least a second bidding behavior utilizing at least said second estimated structure of said market, said characteristics of said market and said relevant bidding model;
predicting, performed by said computer system, a second outcome of said market based on at least said second bidding behavior prediction;
and
determining, performed by said computer system, said auction format for said market by evaluating said first outcome of said market and at least said second outcome of said market.

6 more elements

A computer system comprising:

a processor for executing instructions;
a computer readable medium with said instructions stored thereon, wherein said instructions implement;
a market-characteristic-based-on-historical-auctions-selector configured for selecting characteristics of said market based at least in part on stored historical bids data that includes data for historical auctions performed in the past for a plurality of bidders;
a relevant-bidding-model-selector-based-on-privately-held-bidder-information-and-based-on-segments-of-past-auctions configured for selecting a relevant bidding model that specifies past bidding behavior as a function of information held privately by a bidder, that is determined based at least in part on said past auctions data, and said characteristics of said market based on segments of said past auctions related to a specified item;
an estimated-structure-of-market-selector configured for selecting at least a first and a second estimated structure of said market, wherein said first estimated structure of said market describes at least a first factor that affects how bidders behave and wherein said second estimated structure of said market describes at least a second factor that affects how bidders behave;
a bidding-behavior-based-on-estimated-market-structure-predictor configured for predicting a first bidding behavior utilizing said first estimated structure of said market, said characteristics of said market and said relevant bidding model;
a market-outcome-based-on-bidding-behavior-predictor configured for predicting a first outcome of said market based on said first bidding behavior;
said bidding-behavior-based-on-estimated-market-structure-predictor configured for predicting at least a second bidding behavior utilizing at least said second estimated structure of said market, said characteristics of said market and said relevant bidding model;
said market-outcome-based-on-bidding-behavior-predictor configured for predicting a second outcome of said market based on at least said second bidding behavior prediction;
and
a determiner-of-auction-format-based-on-evaluating-market-outcome configured for determining an auction format by evaluating said first outcome of said market and at least said second outcome of said market.

8 more elements

A computer readable medium having stored thereon computer-executable instructions for causing a computer system to execute the steps in a method for determining an auction format for a market, said method comprising the steps of:

selecting characteristics of said market based at least in part on stored historical bids data that includes data for historical auctions performed in the past for a plurality of bidders;
selecting a relevant bidding model that specifies past bidding behavior as a function of information held privately by a bidder, that is determined based at least in part on said historical auctions data, and said characteristics of said market based on segments of said historical auctions related to a specified item;
selecting at least a first estimated structure of said market, which describes at least a first factor that affects how bidders behave, and a second estimated structure of said market, which describes a second factor that affects how bidders behave, at least in part by inverting said relevant bidding model;
predicting a first bidding behavior utilizing said first estimated structure of said market, said characteristics of said market and said relevant bidding model;
predicting a first outcome of said market based on said first bidding behavior;
predicting at least a second bidding behavior utilizing at least said second estimated structure of said market, said characteristics of said market and said relevant bidding model;
predicting a second outcome of said market based on at least said second bidding behavior prediction;
and
determining said auction format for said market by evaluating said first outcome of said market and at least said second outcome of said market.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 09/903,075Filed 10 Jul 2001
Published: US 2003/0018562 A123 Jan 2003
Granted: 1 Dec 2009
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06Q 10/04
Administration; Management: forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or…
G06Q 30/08
Buying, selling or leasing transactions: auctions
G06Q 40/04
Finance; Insurance; Tax strategies; Processing of corporate or income taxes: trading; Exchange, e.g. stocks, commodities, derivatives or currency…
G06Q 50/188
Legal services: electronic negotiation