Truth revealing market equilibrium

• US 7,788,164 B2
• Filed: 09/15/2005
• Issued: 08/31/2010
• Est. Priority Date: 09/15/2005
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Jain, Kamal, Talwar, Kunal
• Primary Examiner(s): Subramanian; Narayanswamy
• Assistant Examiner(s): Baird; Ed
• Application Number:
  US11/227,454
• Publication Number:
  US 20070061240A1
• Time in Patent Office: 1,811 Days
• Field of Search: 705/37, 705/14, 705/10, 705/36
• US Class Current: 705/37
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

To use market clearing methods to determine market equilibrium, a market clearing situation is established by determining a number of items to be sold at the market price and allotting a number of pseudo items assignable to bids below the market price. Once bids are received for the items, using the number of pseudo items and the actual items as the supply side, and the total funds bid as the demand side, a market clearing price is determinable using a market clearing equilibrium model. Funds assigned to pseudo items are returned or not charged. Further, by selling items only to bids exceeding the market clearing price, such as by setting the market price incrementally above the market clearing price, bidders are encouraged to submit bid prices bid reflecting what the items are worth to them instead of attempting to bid strategically to guess or set the market price.

Claims

1. A method using computer executable instructions, executable by a computing device for setting a market price for an auction of a number of advertising opportunities, each of the advertising opportunities being presentable on a number of pages and operable to present a selectable advertisement, the method comprising:

setting, by the computing device, the market price for the auction of advertising opportunities based on supply and demand, the market price being calculated with a supply side including a number of items to be sold, and a number of pseudo items, and a demand side including received bids, wherein the pseudo items are not real items and neither actually are nor can be sold to bidders but are assignable to bids below the market price;

determining, by the computing device, the number of advertising opportunities by using historical data from an online search engine provider, the online search engine provider to forecast a number of searches performed for search terms conducted on certain days, months or seasons of a year to yield results for a known number of advertising opportunities;

creating, by the computing device, an unspent money slot;

receiving, on the computing device, a plurality of bids for the advertising opportunities, each of the bids including a bid price and an auction budget;

calculating, by the computing device, a market clearing price based on the number of advertising opportunities;

setting, by the computing device, the market price to one of the market clearing price and a value greater than the market clearing price, or allowing a bidder to set the market price with a second highest bid;

selling, by the computing device, advertising opportunities to the bidders submitting bids at or above the market price;

assigning each of the number of advertising opportunities to each of the bids at least equivalent to the market price;

presenting, by the computing device, on web pages that have been generated by the online service provider, advertisements associated with the bidders that have been assigned advertising opportunities; and

refunding money in the unspent money slot.

2. A method of claim 1, wherein the number of advertising opportunities to be sold represents an estimated number of advertising opportunities derived from at least one of:

a known number of advertising opportunities available to be sold;

a body of historical data representing an actual number of advertising opportunities sold; and

a projection of a number of advertising opportunities to be sold.

3. A method of claim 1, further comprising determining the number of pseudo items such that a price of each of the pseudo items is equivalent to each of the bids to which each of the pseudo items is assigned.

4. A method of claim 3, wherein the number of pseudo items is determined using a binary search algorithm.

5. A method of claim 1, wherein the plurality of bids includes:

a plurality of actual bids received from a number of actual bidders; and

a plurality of pseudo bids from a number of pseudo bidders

wherein each of the pseudo bidders submits a bid price and an auction budget equal to a product of a reserve price and the number of rounds.

6. A method of claim 5, further comprising:

determining a first likelihood of each of the advertising opportunities of being selected;

determining a second likelihood of the advertisement being selected, independent of the advertising opportunity in which the selectable advertisement is presented, the second likelihood including;

for each of the advertisements associated with actual bids, the second likelihood includes one of an estimated and a measured likelihood; and

for each of the pseudo bids, the second likelihood is set to one; and

the market clearing price is determined by maximizing a utility of each of the actual bidders and the pseudo bidders where the utility is the product of the bid price, the first likelihood, and the second likelihood.

7. A method of claim 6, further comprising ensuring that only a single advertisement for a single bidder is presented on a single screen using one of:

a matching polytope is a selection of L_i shown as a constraint comprising;

$\stackrel{k}{\underset{j=1}{\sum <br><br>}}<br><br>x_{\mathrm{ij}}<br><br>{\mathrm{\alpha <br><br>}}_j\le <br><br>L_i$

wherein x_ij represents a portion of each of the advertising opportunities j won by the single bidder i, α

_j represents an inherent likelihood of being selected by a user, and for each bidder L_i is chosen such that L₁>

L₂>

. . . >

L_l, and L_i<

α

_i for 1<

i<

min(k, l), and L_i=1 for each of pseudo bidders l through k+l, wherein using the equation in which items are sold and budgets are exhausted, the matching polytope is when all of the items are sold and all of the budgets are exhausted;

an assignment polytope includes assigning a first advertising opportunity to a first bidder for fifty percent and to a second bidder for fifty percent, wherein the assignment polytope is applied to ensure that the same bidder is not assigned more than one advertising opportunity on a page; and

a double stochastic matrix includes a binary search algorithm employed to ensure that there are pseudo items to be assigned to below market price bids to effect a market clearing situation,

wherein the double stochastic matrix is applied to ensure that the same bidder is not assigned more than one advertising opportunity on a page.

8. A method of claim 1, wherein the market clearing price is determined using a Fisher equilibrium model.