Automatic flight management in an online marketplace

• US 7,499,874 B2
• Filed: 12/23/2005
• Issued: 03/03/2009
• Est. Priority Date: 05/28/1999
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Davis, Darren J., Singh, Narinder Pal
• Primary Examiner(s): DURAN, ARTHUR D
• Application Number:
  US11/318,243
• Publication Number:
  US 20060190328A1
• Time in Patent Office: 1,166 Days
• Field of Search: 705/14
• US Class Current: 705/14.54
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0249 based upon budgets or funds
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0257 User requested
• CPC Class Codes: G06Q 30/0264 based upon schedule
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/08 Auctions

Abstract

A database search system includes a database of search terms, each search term associated with a bid amount payable by an advertiser of a plurality of advertisers and a search engine responsive to search queries from searchers for searching the database. A flight management agent is responsive to advertiser-specified parameters for adjusting bid amounts of search listings to manage expenditures over a time interval.

Claims

1. A method for automating management in an online marketplace among a plurality of advertisers and searchers, the method comprising:

maintaining a computer network-accessible database of advertiser search listings, each search listing including at least a bid amount and a search term associated therewith, the bid amount corresponding to economic value given by the associated advertiser to an operator of the online marketplace when network locations of the associated advertiser are referred to a searcher in response to a database query from the searcher;

initializing an automated advertising flight of an advertiser that owns a plurality of search listings by determining a remaining budget and a remaining flight period; and

iteratively and periodically performed by a computer, for each search term (T_i) and rank (j), the following to execute the advertising flight while a time period runs or until an occurrence of a specified event

automatically updating a plurality of flight parameters based on a current state of the marketplace and any updates from the advertiser, wherein the flight parameters are selected from the group consisting of a conversion rate, the bid amount and a corresponding rank, a maximum average cost per click (CPC), and a historical number of clicks for each search term;

maximizing a total profit by iteratively and automatically adjusting the bid amounts associated with at least some of the plurality of search terms until an optimal combination of bid amounts and corresponding plurality of search terms is determined, wherein each iteration calculates an estimated total number of clicks, the bid amounts, a total cost, and a total profit for the advertising flight for comparison with previous iterations;

computing R_max, a highest conversion rate of conversion rates R(T_i, j), of each search term T_i in a set {T₁, T₂, . . . , T_k} at any rank j;

normalizing the number of clicks and the bid amount of each search term at every rank so that all search terms at all ranks have the same conversion rate R_max;

assigning a conversion rate (T_i, j)=R_max at every rank j;

setting a number of variable clicks for the current search term and rank equal to the ratio of the conversion rate for the current term and rank to R_max multiplied by the total number of clicks for the current search term, rank, and the current remaining length of the flight;

setting the current bid for the search term T at rank j as equal to the ratio of R_max to the current conversion rate for the search term T at rank j multiplied by the current bid for the search term T at the current rank j;

re-computing the remaining budget based on a budget amount spent during a current iteration; and

re-computing the remaining flight period based on a flight period expired during the current iteration.

2. The method of claim 1, further comprising:

determining the estimated total number of clicks, the bid amounts, a total cost, and a total profit as the optimal combination such that the bid amounts are minimized, yet simultaneously achieve a plurality of corresponding best possible ranks to maximize profit within the remaining budget.

3. The method of claim 1, further comprising:

sending a report to the advertiser that includes a summary of bid amount changes made automatically on behalf of the advertiser.

4. The method of claim 1, wherein the time period is the remaining flight period.

5. The method of claim 1, further comprising:

ignoring a current combination within an iteration of automatically adjusting the bid amounts if its average bid is greater than the maximum average CPC specified by the advertiser.

6. The method of claim 1, further comprising:

ignoring a current combination within an iteration of automatically adjusting the bid amounts if the total cost is greater than the remaining budget.

7. The method of claim 1, wherein the optimal combination of the plurality of search terms and a plurality of possible ranks is determined by comparing the average bid, which is the total cost divided by the total number of clicks, with the total profit.

8. The method of claim 1, further comprising:

searching for a lowest average bid while iteratively adjusting the bid amounts, wherein the average bid is defined as the total cost divided by the total number of estimated clicks; and

returning a current combination as the optimal combination if the average bid of the current combination of search terms and corresponding bid amounts is less than that of any previous combination.

9. The method of claim 1, further comprising:

removing a plurality of ranks associated with at least some of the plurality of search terms that are likely to not be a part of the optimal combination, to optimize the iterations required within the advertising flight.

10. The method of claim 9, further comprising:

estimating an original bid amount that is the same for each of the plurality of search terms such that the remaining budget is approximately spent during the remainder of the flight period wherein “

approximately spent”

is defined by the remaining budget being spent within a predetermined amount of economic value above or below a budget specified by the advertiser; and

selecting a band of ranks for each of the plurality of search terms that corresponds to the original bid, wherein ranks outside of each band are removed.