US2010228636A1PendingUtilityA1

Risk premiums for conversion-based online advertisement bidding

63
Assignee: GOOGLE INCPriority: Mar 4, 2009Filed: Mar 4, 2009Published: Sep 9, 2010
Est. expiryMar 4, 2029(~2.6 yrs left)· nominal 20-yr term from priority
G06Q 40/12G06Q 30/0601G06Q 30/0276G06Q 30/02G06Q 30/0275
63
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

An advertiser specifies a conversion-based bid for a conversion event associated with an ad. If a conversion event occurs for the ad, an effective conversion-based bid can be adjusted by a risk premium associated with the ad. An account associated with the advertiser can be debited based upon the adjusted effective conversion-based bid.

Claims

exact text as granted — not AI-modified
1 . A computer-implemented method comprising:
 determining at an advertisement server whether a specified conversion-based bid associated with an online advertisement specified by an advertiser qualifies the online advertisement for placement by the advertisement server;   if a conversion event for the online advertisement occurs, adjusting an effective conversion-based bid with a risk premium allocation subsystem, the adjustment being based on a risk premium associated with the online advertisement, the effective conversion-based bid being derived from the specified conversion-based bid for the online advertisement; and   debiting an account associated with the advertiser with the advertisement server, the debiting being based upon the adjusted effective conversion-based bid.   
     
     
         2 . The method of  claim 1 , wherein determining whether the specified conversion-based bid qualifies the online advertisement for placement comprises performing an impression based auction. 
     
     
         3 . The method of  claim 2 , wherein the impression based auction comprises a second-price auction using impression based bidding. 
     
     
         4 . The method of  claim 2 , further comprising converting the specified conversion-based bid to an impression-based bid using a predicted conversion rate and a predicted click-through rate associated with the auction, the impression-based bid facilitating participation of the advertisement in the impression-based auction. 
     
     
         5 . The method of  claim 4 , further comprising if a conversion event for the online advertisement occurs, converting an effective impression-based bid from the impression-based auction to provide the effective conversion-based bid using the predicted conversion rate and predicted click-through rate. 
     
     
         6 . The method of  claim 1 , wherein the risk premium adjusts the effective conversion-based bid based on a risk that the predicted conversion rate is incorrect. 
     
     
         7 . The method of  claim 1 , wherein the risk premium adjusts the effective conversion-based bid based on a risk that the advertiser does not accurately report conversions from the advertisement impression. 
     
     
         8 . The method of  claim 1 , wherein the risk premium comprises the difference between the effective conversion-based bid and the specified conversion-based bid. 
     
     
         9 . The method of  claim 1 , wherein the risk premium comprises a percentage of the effective conversion-based bid. 
     
     
         10 . The method of  claim 1 , wherein the risk premium comprises a fixed fee added to the effective conversion-based bid. 
     
     
         11 . The method of  claim 1 , wherein the risk premium comprises a subscription based fee charged to the advertiser for use of conversion based bids. 
     
     
         12 . The method of  claim 1 , further comprising automatically mapping one or more impression context features to a predicted conversion rate using a learning model. 
     
     
         13 . The method of  claim 12 , wherein the learning model is a machine learning system model that includes rules for mapping one or more impression context features to a predicted conversion rate using conversion data. 
     
     
         14 . The method of  claim 12 , further comprising:
 normalizing the predicted conversion rate to remove the effect of different conversion definitions.   
     
     
         15 . The method of  claim 1 , wherein the risk premium is applied pre-conversion by discounting the specified conversion-based bid using the risk premium prior to performing an auction for placement of the advertisement by the advertisement server. 
     
     
         16 . The method of  claim 1 , wherein the risk premium is applied post-conversion by applying the risk premium to the effective conversion based bid an up to the specified conversion-based bid. 
     
     
         17 . A computer-readable medium having instructions stored thereon, which, when executed by a processor, causes the processor to perform operations comprising:
 determining whether a maximum conversion-based bid associated with an online advertisement specified by an advertiser qualifies the online advertisement for placement;   if a conversion event for the online advertisement occurs, increasing an effective conversion-based bid using a risk premium associated with the online advertisement, the effective conversion-based bid being derived from the maximum conversion-based bid for the online advertisement; and   debiting an account associated with the advertiser based upon the adjusted target conversion-based bid.   
     
     
         18 . The computer-readable medium of  claim 17 , wherein determining whether the maximum conversion-based bid qualifies the online advertisement for placement comprises performing an impression based auction. 
     
     
         19 . The computer-readable medium of  claim 18 , wherein the impression based auction comprises a second-price auction using impression based bidding. 
     
     
         20 . The computer-readable medium of  claim 18 , further operable to cause the processor to perform operations comprising converting the maximum conversion-based bid to an impression-based bid using a predicted conversion rate and a predicted click-through rate associated with the auction, the impression-based bid facilitating participation of the advertisement in the impression-based auction. 
     
     
         21 . The computer-readable medium of  claim 20 , further operable to cause the processor to perform operations comprising if a conversion event for the online advertisement occurs, converting an effective impression-based bid from the impression-based auction to provide the effective conversion-based bid using the predicted conversion rate and predicted click-through rate. 
     
     
         22 . The computer-readable medium of  claim 17 , wherein the risk premium adjusts the effective conversion-based bid based on a risk that the predicted conversion rate is incorrect. 
     
     
         23 . The computer-readable medium of  claim 17 , wherein the risk premium adjusts the effective conversion-based bid based on a risk that the advertiser does not accurately report conversions from the advertisement impression. 
     
     
         24 . The computer-readable medium of  claim 17 , wherein the risk premium comprises the difference between the effective conversion-based bid and the maximum conversion-based bid. 
     
     
         25 . The computer-readable medium of  claim 17 , wherein the risk premium comprises a percentage of the effective conversion-based bid. 
     
     
         26 . The computer-readable medium of  claim 17 , wherein the risk premium comprises a fixed fee added to the effective conversion-based bid. 
     
     
         27 . The computer-readable medium of  claim 17 , wherein the risk premium comprises a subscription based fee charged to the advertiser for use of conversion based bids. 
     
     
         28 . The computer-readable medium of  claim 17 , further operable to cause the processor to perform operations comprising automatically mapping one or more impression context features to a predicted conversion rate using a learning model. 
     
     
         29 . The computer-readable medium of  claim 28 , wherein the learning model is a machine learning system model that includes rules for mapping one or more impression context features to a predicted conversion rate using conversion data. 
     
     
         30 . The computer-readable medium of  claim 28 , further operable to cause the processor to perform operations comprising normalizing the predicted conversion rate to remove the effect of different conversion definitions. 
     
     
         31 . A system comprising:
 an advertisement server operable to determine whether a conversion-based bid associated with an online advertisement specified by an advertiser qualifies the online advertisement for placement; and   a risk premium allocation subsystem operable to adjust an effective conversion-based bid using a risk premium in the event of a conversion associated with the online advertisement, the effective conversion-based bid being derived from the specified conversion-based bid for the online advertisement;   wherein the advertisement server is further operable to debit an account associated with the advertiser based upon the adjusted effective conversion-based bid.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.