Forecasting and booking of inventory atoms in content delivery systems

• US 8,996,402 B2
• Filed: 08/02/2010
• Issued: 03/31/2015
• Est. Priority Date: 08/02/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Priyadarshan, Eswar, Grigorovici, Dan Marius, Abdala, Omar, Mukherjee, Prasenjit
• Primary Examiner(s): Myhre, James W
• Application Number:
  US12/848,370
• Publication Number:
  US 20120030008A1
• Time in Patent Office: 1,702 Days
• Field of Search: 705/14.42, 705/14.48
• US Class Current: 705/14.42
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0249 based upon budgets or funds

Abstract

Systems and methods for planning and booking advertising campaigns are provided. In operation, a booking engine generates a collection of proposed campaigns in response to a campaign request, where the each of the proposed campaigns corresponds to a scenario of atom availability. Such scenarios can account for possible or anticipated changes in the number and cost of atoms or any other changes of interest to the advertiser. The availability for the atoms in the campaign request can be projected using the past history and the known future unavailability of the atoms and is further modified to account for the variation in atom availability associated with each scenario. Thereafter, the booking engine can present the results for each scenario to the advertiser and allow him to select a campaign.

Claims

1. A method comprising:

receiving a campaign request from a user terminal comprising at least one requested inventory slot, a specified performance criteria, and at least one match criteria, the requested inventory slot identifying a portion of atoms from an inventory space managed by a content delivery system, wherein each atom represents a portion of traffic for a segment of characteristics;

retrieving scenario modeling parameters defining atom availability scenarios;

assembling, via a processor, a proposed campaign for each of the atom availability scenarios, the assembling comprising;

computing estimates of an availability of the atoms in the inventory slot for each of the atom availability scenarios, the estimates for each of the atom availability scenarios based at least on a corresponding portion of the scenario modeling parameters, a history of the atoms in the inventory space, and known future unavailability of the atoms in the inventory space, wherein the known future unavailability of atoms is based on booked campaigns or reserved inventory atoms;

generating the proposed campaign for each of the atom availability scenarios by selecting atoms for the proposed campaign based on at least a one of the estimates of the availability of atoms for the atom availability scenarios,

calculating an estimated performance for the proposed campaign based on the history of the atoms in the inventory space and the known future unavailability of the atoms, and

when the estimated performance for the proposed campaign fails to meet the specified performance criteria, regenerating the proposed campaign using recomputed estimates, the recomputed estimates applying to regenerated proposed campaigns comprising at least one atom outside the inventory slot and meeting the match criteria, the match criteria specifying an alternative segment characteristic for selecting alternate atoms thereby permitting an allowable variation in the at least one requested inventory slot to satisfy the specified performance criteria; and

providing the proposed campaign to the user terminal.

2. The method of claim 1, wherein the match criteria specifies at least one of an allowable variation in channel characteristics, spatial-temporal characteristics, behavioral characteristics, or demographic characteristics, and wherein the known future unavailability of the atoms is used to calculate the estimated performance by indicating a conflict between proposed atoms for the proposed campaign and the proposed atoms for another campaign.

3. The method of claim 1, wherein providing further comprises:

selecting the portion of the atom availability scenarios to be presented based on the estimated performances and the performance criteria, wherein the proposed campaign is generated based on an interval cap that limits a number of atoms that may be assigned to the proposed campaign for a time interval.

4. The method of claim 1, wherein at least a portion of the scenario modeling parameters are defined in the campaign request, and wherein each atom represents the portion of traffic for the segment of characteristics comprising an amount of traffic, a specific ethnicity, an age parameter, and an income parameter, the availability scenarios comprising different models of changes in the amount of traffic, specific ethnicity, age parameter, and income parameter.

5. The method of claim 1, wherein computing estimates of an availability of the atoms further comprises:

responsive to at least one of the inventory atoms in the proposed slot having a status of unavailable resulting from being associated with at least one booked inventory slot, determining whether to adjust the inventory atoms for at least one of the proposed inventory slot or a previously booked inventory slot in the inventory space associated with the at least one unavailable inventory atom.

6. The method of claim 1, the campaign request comprising a budget defining an acceptable cost associated with the proposed campaign, the acceptable cost being based on a cost of identified atoms in the proposed campaign, the cost of the identified atoms being calculated based on at least one of a demand associated with the identified atoms and a performance history associated with the identified atoms.

7. The method of claim 6, wherein the cost of the identified atoms is calculated based on a projected future demand for the identified atoms, the projected future demand being determined using one of a neural network, a fuzzy method, a Bayesian method, or a tree-based greedy algorithm method.

8. The method of claim 1, the specified performance criteria specifying a maximum number of atoms for the proposed campaign.

9. The method of claim 1, the specified performance criteria specifying a precision value defining a degree of match.

10. The method of claim 1, the match criteria specifying a maximum number of atoms that can be used from outside the inventory slot.

11. The method of claim 1, further comprising determining a relative priority of the proposed campaign and a second campaign, wherein the relative priority is used to resolve a conflict created by an atom booked for both the proposed campaign and the second campaign.

12. The method of claim 1, wherein the relative priority indicates an order for allocating each of the atoms to campaigns during a next time interval, wherein the priority ranking is based on a targeting granularity of the campaign request.

13. The method of claim 1, wherein the relative priority is determined based on a pre-defined priority criteria, the pre-defined priority criteria being based on a remaining time associated with each of active campaign, and wherein the relative priority is used to allocate an atom required by multiple campaigns to an active campaign selected based on the relative priority.

14. The method of claim 1, wherein the inventory slot identifies the portion of atoms from the inventory space, and wherein at least one of the atoms in the portion are future atoms.

15. A content delivery system, comprising:

a processor;

at least one storage element for storing a history and known future unavailability of atoms in an inventory space managed by a content delivery system, scenario modeling parameters defining atom availability scenarios for the atoms in the inventory space, and at least one campaign request, the campaign request comprising a specified performance criteria, at least one match criteria, and at least one requested inventory slot identifying a portion of the atoms in the inventory space, wherein each atom represents a portion of traffic for a segment of characteristics;

a booking module configured to control the processor to process the campaign request, the processing comprising retrieving the campaign request, the scenario modeling parameters, the history, and the known unavailability of the atoms from the storage element, assemble proposed campaigns for each of the atom availability scenarios, and present the proposed campaigns for at least a portion of the atom availability scenarios at a user terminal associated with the campaign request, wherein the assembling comprises;

computing estimates of an availability of the atoms in the inventory slot for each of the atom availability scenarios based at least on a corresponding portion of the scenario modeling parameters, the history, and the known unavailability of the atoms from the storage element, wherein the known future unavailability of atoms is based on booked campaigns or reserved inventory atoms,

generating a proposed campaign for each one of the atom availability scenarios, the generating comprising selecting atoms based on at least one of the estimates associated with the one of the atom availability scenarios, and

calculating an estimated performance for the proposed campaigns based on the history of the atoms in the inventory space and the known future unavailability of the atoms, wherein when the estimated performance for a proposed campaign fails to meet the specified performance criteria, regenerating the proposed campaign using recomputed estimates, the recomputed estimates applying regenerated proposed campaigns comprising at least one atom outside the inventory slot and meeting the match criteria, the at least one match criteria specifying at least one alternative segment characteristic for selecting alternate atoms, thereby permitting an allowable variation in the at least one requested inventory slot to satisfy the specified performance criteria; and

an interface module configured to control the processor to deliver one of the presented campaigns in response to selection of the one of the presented campaigns at the user terminal.

16. The system of claim 15, wherein the match criteria specifies at least one of an allowable variation in channel characteristics, spatial-temporal characteristics, behavioral characteristics, or demographic characteristics.

17. The system of claim 15, wherein the processing element is further configured for presenting the proposed campaigns meeting the performance criteria.

18. A non-transitory computer-readable medium having stored therein instructions which, when executed by a processor, cause the processor to perform operations comprising:

receiving a campaign request from a user terminal comprising at least one requested inventory slot, a specified performance criteria, one or more match criteria, and one or more scenario modeling parameters, the requested inventory slot identifying a requested portion of atoms from an inventory space during one or more requested time intervals, and the scenario modeling parameters defining one or more atom availability scenarios, wherein each atom represents a portion of traffic for a segment of characteristics;

assembling a proposed campaign for each one of the atom availability scenarios, the assembling comprising;

computing estimates of an availability of the atoms in the inventory slot for each of the atom availability scenarios, the estimates for each of the atom availability scenarios based at least on a corresponding portion of the one or more scenario modeling parameters, a history of the atoms in the inventory space, and a known future unavailability of the atoms in the inventory space, wherein the known future unavailability of atoms is based on booked campaigns or reserved inventory atoms,

generating the proposed campaign for each one of the atom availability scenarios, the generating comprising selecting atoms based on at least a one of the estimates associated with the one of the atom availability scenarios, and

calculating an estimated performance for the proposed campaign based on the history of the atoms in the inventory space and the known future unavailability of the atoms, wherein when the estimated performance for the proposed campaign fails to meet the specified performance criteria, regenerating the proposed campaign using recomputed estimates, the recomputed estimates applying to regenerated proposed campaigns comprising at least one atom outside the inventory slot and meeting the one or more match criteria, the at least one match criteria specifying at least one alternative segment characteristic for selecting alternate atoms, thereby permitting an allowable variation in the at least one requested inventory slot to satisfy the specified performance criteria; and

presenting the proposed campaign for at least a portion of the atom availability scenarios at the user terminal.

19. The non-transitory computer-readable medium of claim 18, wherein the one or more match criteria specifies at least one of an allowable variation in channel characteristics, spatial-temporal characteristics, behavioral characteristics, or demographic characteristics.

20. The non-transitory computer-readable medium of claim 18, wherein the step of presenting further comprises:

selecting the portion of the atom availability scenarios to be presented based on the estimated performance and the performance criteria.

21. A campaign booking system, comprising:

a processor;

at least one storage element for storing a history and known future unavailability of atoms in an inventory space managed by a content delivery system, first scenario modeling parameters, and at least one campaign request, the campaign request comprising at least one requested inventory slot, second scenario modeling parameters, a match criteria, and a specified performance criteria, the requested inventory slot identifying a portion of the atoms from the inventory space, and combinations of the first and the second scenario modeling parameters defining one or more atom availability scenarios at the content delivery system, wherein each atom represents a portion of traffic for a segment of characteristics;

an analysis module configured to control the processor to process the campaign request, wherein the processing comprises retrieving the campaign request, the first and second scenario modeling parameters, and the history and the known future unavailability of the atoms from the storage element, assemble proposed campaigns for each of the atom availability scenarios, and present the proposed campaigns for at least a portion of the atom availability scenarios at a user terminal associated the campaign request, wherein the assembling comprises;

computing estimates of an availability of the atoms in the inventory slot for each of the atom availability scenarios based at least one of the combinations of the first and the second scenario modeling parameters, the history, and the known unavailability of the atoms from the storage element, wherein the known future unavailability of atoms is based on booked campaigns or reserved inventory atoms,

generating a proposed campaign for each one of the atom availability scenarios, the generating comprising selecting atoms based on at least one of the estimates associated with the one of the atom availability scenarios, and

calculating an estimated performance for the proposed campaigns based on the history of the atoms in the inventory space and the known future unavailability of the atoms, wherein when the estimated performance for a proposed campaign fails to meet the specified performance criteria, regenerating the proposed campaign using recomputed estimates, the recomputed estimates applying to regenerated proposed campaigns comprising at least one atom outside the inventory slot and meeting the match criteria, the at least one match criteria specifying at least one alternative segment characteristic for selecting alternate atoms, thereby permitting an allowable variation in the at least one requested inventory slot to satisfy the specified performance criteria; and

a booking module configured to control the processor to deliver one of the presented campaigns to the content delivery system in response to selection of the one of the presented campaigns at the user terminal.

22. The system of claim 21, wherein the match criteria specifies at least one of an allowable variation in channel characteristics, spatial-temporal characteristics, behavioral characteristics, or demographic characteristics.

23. The system of claim 21, wherein the processing element is further configured for presenting the proposed campaigns meeting the performance criteria.