Traffic estimator

• US 8,099,326 B2
• Filed: 10/31/2006
• Issued: 01/17/2012
• Est. Priority Date: 06/01/2005
• Status: Expired due to Fees

• Current Assignee: LOT Network Inc.
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Gardner, Robert, Clingman, Eliot, Ketchum, Russell Kevin, Beauchamp, Scott, Steelberg, Ryan, Steelberg, Chad
• Primary Examiner(s): Boveja, Namrata
• Assistant Examiner(s): HOAR, COLLEEN A
• Application Number:
  US11/554,934
• Publication Number:
  US 20080021791A1
• Time in Patent Office: 1,904 Days
• Field of Search: None
• US Class Current: 705/14.64
• CPC Class Codes: G06Q 30/0267 Wireless devices
• CPC Class Codes: G06Q 30/0272 Period of advertisement exposure
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: H04H 20/38 Arrangements for distribution where lower stations, e.g. receivers, interact with the broadcast
• CPC Class Codes: H04H 60/06 Arrangements for scheduling broadcast services or broadcast-related services
• CPC Class Codes: H04H 60/33 Arrangements for monitoring the users' behaviour or opinions
• CPC Class Codes: H04H 60/66 for using the result on distributors' side
• CPC Class Codes: H04L 63/0428 wherein the data content is protected, e.g. by encrypting or encapsulating the payload
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 67/53 using third party service providers
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context

Abstract

Systems, methods, and a user interface are used for bidding on media plays. The user can specify criteria for play of the media play, including times, stations, and budgets. A traffic estimator uses historical data to estimate bids and auctions, and the likelihood of winning, for generating listener traffic based on the criteria.

Claims

1. A computer-implemented method comprising:

receiving, by a server system from a client system associated with a user, criteria for media play placement in a media feed;

generating a list of available ads based on the received criteria;

for each one of the available ads on the generated list,

selecting, by the server system, an overspending cost per thousand (CPM) bid and an underspending CPM bid for the one of the available ads,

defining, by the server system, a bid interval that includes the overspending CPM bid as one endpoint, and the underspending CPM bid as the other endpoint,

iteratively, until the bid interval has converged within a threshold range;

applying, by the server system, a reguli falsi process to the bid interval until the bid interval converges, then, when a range of the converged bid interval is larger than the threshold range,

applying, by the server system, a bisection process to the converged bid interval for a predetermined period of time, and

outputting, as an expected CPM bid for the one of the available ads, a result of applying the reguli falsi process and the bisection process; and

generating, by the server system, bids for the available ads on the generated list as the corresponding expected CPM bids that have been output via the reguli falsi process and the bisection process.

2. The computer-implemented method of claim 1, wherein the expected CPM is output, by the server system, as the result of iteratively applying the reguli falsi process and the bisection process.

3. The computer-implemented method of claim 1, wherein the selecting of the overspending CPM bid and the underspending CPM bid comprises:

dividing a plurality of media plays in sets of media plays, each set associated with a criterion of the received criteria for media play placement;

accessing historical information related to bidding for past media play placement in the media feed for each criterion of the received criteria for media play placement; and

performing the selecting of the overspending CPM bid and the underspending CPM bid in response to failing to obtain from the user respective maximum CPMs corresponding to the received criteria for media play placement.

4. The computer-implemented method of claim 3, further comprising:

generating, by the server system, a map of probability density functions (PDFs); and

storing, in the generated map of PDFs, respective portions of the historical information associated with respective criteria for media play placement in a media feed,

wherein said accessing the historical information includes retrieving PDFs from the generated map of PDFs corresponding to the received criteria, and

wherein said selecting the overspending CPM bid and the underspending CPM bid is based on the retrieved PDFs corresponding to the received criteria.

5. The computer-implemented method of claim 4, further comprising:

generating, by the server system, an additional probability density function map; and

storing seasonal information in the generated additional probability density function map,

wherein said selecting the overspending CPM bid and the underspending CPM bid is further based on the additional probability density function map.

6. The computer implemented method of claim 1, wherein the user comprises an advertiser.

7. The computer implemented method of claim 1, wherein the received criteria for media placement in the media feed comprise radio market areas, radio stations, dayparts, a budget for a time interval, type of radio stations, and listener demographics.

8. The computer implemented method of claim 7 wherein

the dividing the plurality of plays in the sets of media plays includes:

generating a list of radio stations based on the received criteria; and

generating a list of available ads for the radio stations in said time interval,

the accessing the historical information related to bidding for the past media play placement includes determining historical bids for dayparts of the radio stations in the list, and

the method further comprises estimating, by applying the reguli falsi process and the bisection process to the bid interval, respective CPMs for selected ads of the generated list of available ads for each of the received dayparts, such that a cost of the total estimated CPMs is less than or equal to the received budget for the time interval.

9. A computer program product stored on a non-transitory computer readable medium that when executed by data processing apparatus causes the data processing apparatus to perform operations comprising:

receiving, from a client system associated with a user, criteria for media play placement in a media feed;

generating a list of available ads based on the received criteria;

for each one of the available ads on the generated list,

selecting an overspending cost per thousand (CPM) bid and an underspending CPM bid for the one of the available ads,

defining a bid interval that includes the overspending CPM bid as one endpoint, and the underspending CPM bid as the other endpoint,

iteratively, until the bid interval has converged within a threshold range;

applying a reguli falsi process to the bid interval until the bid interval converges, then, when a range of the converged bid interval is larger than the threshold range,

applying a bisection process to the converged bid interval for a predetermined period of time, and

outputting, as an expected CPM bid for the one of the available ads, a result of applying the reguli falsi process and the bisection process; and

generating bids for the available ads on the generated list as the corresponding expected CPM bids that have been output via the reguli falsi process and the bisection process.

10. The computer program product of claim 9, wherein the expected CPM is output as the result of iteratively applying the reguli falsi process and the bisection process.

11. The computer program product of claim 9, wherein the operations further comprise:

dividing a plurality of media plays in sets of media plays, each set associated with the one a criterion of the received criteria for media play placement;

accessing historical information related to bidding for past media play placement in the media feed for each criterion of the received criteria for media play placement; and

performing the selecting of the overspending CPM bid and the underspending CPM bid in response to failing to obtain from the user respective maximum CPMs corresponding to the received criteria for media play placement.

12. The computer program product of claim 11, the operations further comprise:

generating a map of probability density functions (PDFs); and

storing, in the generated map of PDFs, respective portions of the historical information associated with respective criteria for media play placement in a media feed,

wherein said accessing the historical information includes retrieving PDFs from the generated map of PDFs corresponding to the received criteria, and

wherein said selecting the overspending CPM bid and the underspending CPM bid is based on the retrieved PDFs corresponding to the received criteria.

13. The computer program product of claim 12, wherein the operations further comprise:

generating an additional probability density function map; and

storing seasonal information in the generated additional probability density function map,

wherein said selecting the overspending CPM bid and the underspending CPM bid is further based on the additional probability density function map.

14. The computer program product of claim 9, wherein the received criteria for media placement in the media feed comprise radio market areas, radio stations, dayparts, a budget for a time interval, type of radio stations, and listener demographics.

15. The computer program product of claim 14 wherein

said dividing the plurality of plays in the sets of media plays includes:

generating a list of radio stations based on the received criteria; and

generating a list of available ads for the radio stations in said time interval,

said accessing the historical information related to bidding for the past media play placement includes determining historical bids for dayparts of the radio stations in the list, and

the operations further comprise estimating, by applying the reguli falsi process and the bisection process to the bid interval, respective CPMs for selected ads of the generated list of available ads for each of the received dayparts, such that a cost of the total estimated CPMs is less than or equal to the received budget for the time interval.

16. A system comprising:

one or more processors communicatively coupled with a client system associated with an advertiser; and

memory associated with the one or more processors and configured to store instructions that when executed by the one or more processors cause the system to perform operations comprising;

receiving, from a client system associated with a user, criteria for media play placement in a media feed;

generating a list of available ads based on the received criteria;

for each one of the available ads on the generated list,

selecting an overspending cost per thousand (CPM) bid and an underspending CPM bid for the one of the available ads,

defining a bid interval that includes the overspending CPM bid as one endpoint, and the underspending CPM bid as the other endpoint,

iteratively, until the bid interval has converged within a threshold range;

applying a reguli falsi process to the bid interval until the bid interval converges, then, when a range of the converged bid interval is larger than the threshold range,

applying a bisection process to the converged bid interval for a predetermined period of time, and

outputting, as an expected CPM bid for the one of the available ads, a result of applying the reguli falsi process and the bisection process; and

generating bids for the available ads on the generated list as the corresponding expected CPM bids that have been output via the reguli falsi process and the bisection process.

17. The system of claim 16, wherein the expected CPM is output as the result of iteratively applying the reguli falsi process and the bisection process.

18. The system of claim 16, wherein the operations further comprise:

dividing a plurality of media plays in sets of media plays, each set associated with a criterion of the received criteria for media play placement;

accessing historical information related to bidding for past media play placement in the media feed for each criterion of the received criteria for media play placement; and

performing the selecting of the overspending CPM bid and the underspending CPM bid in response to failing to obtain from the user respective maximum CPMs corresponding to the received criteria for media play placement.

19. The system of claim 18, wherein the operations further comprise

generating a map of probability density functions (PDFs) corresponding to respective portions of the historical information associated with respective criteria for media play placement in a media feed;

generating an additional probability density function map based on seasonal information;

storing in the memory the generated maps;

retrieving PDFs from the stored maps; and

performing said selecting the overspending CPM bid and the underspending CPM bid based on the retrieved PDFs.