Method and apparatus for determining promotion pricing parameters

• US 10,192,243 B1
• Filed: 06/10/2013
• Issued: 01/29/2019
• Est. Priority Date: 06/10/2013
• Status: Active Grant

• Current Assignee: Groupon Incorporated
• Original Assignee: Groupon Incorporated
• Inventors: Genc-Kaya, Latife, Lai, Kamson, Wicha, Francisco Jose Larrain, L'Huillier, Gaston
• Primary Examiner(s): Sittner, Matthew T
• Assistant Examiner(s): Ansari, Azam A
• Application Number:
  US13/913,887
• Time in Patent Office: 2,059 Days
• Field of Search: 705 1446
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising

Abstract

A method, apparatus, and computer program product are disclosed to improve selection of promotion pricing parameters. The method may determine one or more promotion pricing parameters for a promotion that is offered by a promotion and marketing service. The method includes generating one or more predictive models based on historical promotion performance data and generating a revenue equation using the one or more predictive models. The revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the one or more predictive models. The method further includes determining an estimated revenue using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation, and selecting at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue. A corresponding apparatus and computer program product are also provided.

Claims

1. A method for providing, via a merchant interface, one or more dynamically updated pricing parameters for a promotion and performing continued analysis of promotion performance data for the promotions with established pricing parameters, resulting in a positive feedback loop by which predictive models are continually refined and improved to provide even more accurate predictions of optimal pricing parameters, the method comprising:

generating a demand model to determine the impact of various promotion parameters on the size of past promotion offerings, based on historical promotion performance data, the historical promotion performance data retrieved or received from a historical promotion performance database, wherein the demand model is generated by a regression analysis of the historical promotion performance data, the regression analysis providing a model for predicting a promotion size based on various promotion parameters, wherein the regression analysis is employed to ascertain the correlations between particular parameters and promotion size;

generating a margin model to determine a margin for a first entity for each sale of the promotion, the margin being a portion of an accepted value received by the first entity, that ensures both (i) at least a minimum ROI for the merchant, such that when the promotion is redeemed by a consumer towards the purchase of particular goods, services or experiences offered by the merchant, the merchant receives the minimum ROI from the first entity to account for at least the portion of a price of the particular goods, services or experiences provided to the consumer, while concurrently (ii) establishing that a minimum amount of revenue, in total, is generated by a sale of the promotion,

wherein the margin model is generated by examining the merchant ROI for past promotions with various parameters, and calculating a maximum margin available to the first entity to ensure the minimum ROI,

each of the demand model and the margin model configured to assist with selection of promotion pricing parameters, to determine promotion pricing parameters, or generate promotions with the determined pricing parameters,

wherein generation of the demand model and the margin model comprises

performing a regression analysis to determine an impact of each of one or more promotion parameters,

wherein promotion parameters comprise promotion pricing parameters, wherein each of the one or more predictive models are a result of machine learning algorithms that use the historical promotion performance data as a training set,

wherein the historical promotion performance data employed to generate the promotion performance models comprises one or more of a type of promotion, a merchant category, a discount level, the accepted value of the promotion, a date range associated with the promotion, a number of impressions received for the promotion, a number of promotions offered, a redemption rate of the promotion, and a refund rate of the promotion;

generating a revenue equation using the demand model and the margin model based on a user-specified set of promotion values, wherein the revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the demand model and the margin model,

wherein the generation of the revenue equation comprises;

determining a set of potential promotion parameters including at least a minimum value and maximum value for each promotion parameter based on the historical promotion performance data, and identifying input values within a predefined number of standard deviations of the means of given combinations of promotion parameters;

determining, using a processor, an estimated revenue derived by the promotion and marketing service from predicted sales of the promotion using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation;

selecting at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue, wherein the selected at least one of the input sets of promotion pricing parameters comprise a selected promotion margin received by the promotion and marketing service for sales of the promotion; and

providing the selected at least one of the input sets of promotion pricing parameters to a merchant via a merchant interface;

receiving an indication of a merchant selection of one or more of the selected at least one of the input sets; and

generating the promotion using the selected at least one of the input sets of promotion pricing parameters in response to receiving the indication;

monitoring one or more performance characteristics of the promotion;

adding the one or more performance characteristics of the promotion to the historical promotion performance data; and

updating at least one of the demand model and the margin model based on the one or more performance characteristics of the promotion,

wherein the regression analysis is calculated in accordance with;

log q=α

₁ log p+α

₂ log d+α

₃c+α

₄sc+α

₅ds+α

₆di+α

₇r+α

₈

wherein each of the values are constants weights to be derived via the regression analysis, p is a unit price, d is the discount c is a category, sc is a subcategory, ds is a promotion service category, di is a division, and r is a merchant quality score, and

wherein for a given merchant, the category, subcategory, division, promotion service category, and merchant quality score is known and fixed, particular portions of an equation to predict promotion size are constant, and after accounting for the fixed factors, the size of a particular promotion is calculated by;

log q=α

₁ log p+α

₂ log d+α

₀

wherein α

₀ is a constant representing the fixed values for the particular promotion.

2. The method of claim 1, wherein the historical promotion performance data comprises promotion parameters used for past promotions and performance characteristics of the past promotions.

3. The method of claim 2, wherein the performance characteristics comprise at least one of a promotion redemption rate, a promotion size, or a promotion refund rate.

4. The method of claim 2, wherein the promotion parameters comprise at least one of a promotion accepted value, a promotion promotional value, a promotion residual value, or a merchant category.

5. The method of claim 1, wherein the revenue equation is generated using the demand model and the margin model, and wherein the estimated revenue is calculated by multiplying the promotion size derived from the demand model by the margin value derived from the margin model.

6. The method of claim 5, wherein the margin model is employed to determine the margin value that results in at least a threshold merchant ROI for a merchant associated with the promotion.

7. The method of claim 6, wherein the threshold merchant ROI is zero.

8. The method of claim 1, wherein the one or more input sets of promotion pricing parameters are selected to maximize the estimated revenue.

9. The method of claim 1, further comprising generating a promotion using at least one of the one or more input sets of promotion pricing parameters.

10. The method of claim 1, wherein the selected input set of promotion pricing parameters comprise a margin value, and wherein the method further comprises:

determining a promotion cost based on the margin value; and

presenting the promotion cost to a merchant for approval.

11. The method of claim 10, further comprising receiving approval of the promotion cost and, in response to receiving the approval, generating the promotion with the selected input set of promotion pricing parameters.

12. An apparatus for providing, via a merchant interface, one or more dynamically updated pricing parameters for a promotion and performing continued analysis of promotion performance data for the promotions with established pricing parameters, resulting in a positive feedback loop by which predictive models are continually refined and improved to provide even more accurate predictions of optimal pricing parameters, the method comprising:

generate a demand model to determine the impact of various promotion parameters on the size of past promotion offerings, based on historical promotion performance data, the historical promotion performance data retrieved or received from a historical promotion performance database, wherein the demand model is generated by a regression analysis of the historical promotion performance data, the regression analysis providing a model for predicting a promotion size based on various promotion parameters, wherein the regression analysis is employed to ascertain the correlations between particular parameters and promotion size;

generate a margin model to determine a margin for a first entity for each sale of the promotion, the margin being a portion of an accepted value received by the first entity, that ensures both (i) at least a minimum ROI for the merchant, such that when the promotion is redeemed by a consumer towards the purchase of particular goods, services or experiences offered by the merchant, the merchant receives the minimum ROI from the first entity to account for at least the portion of a price of the particular goods, services or experiences provided to the consumer, while concurrently (ii) establishing that a minimum amount of revenue, in total, is generated by a sale of the promotion,

wherein the margin model is generated by examining the merchant ROI for past promotions with various parameters, and calculating a maximum margin available to the first entity to ensure the minimum ROI,

each of the demand model and the margin model configured to assist with selection of promotion pricing parameters, to determine promotion pricing parameters, or generate promotions with the determined pricing parameters,

wherein generation of the demand model and the margin model comprises

performing a regression analysis to determine an impact of each of one or more promotion parameters,

wherein promotion parameters comprise promotion pricing parameters, wherein each of the one or more predictive models are a result of machine learning algorithms that use the historical promotion performance data as a training set,

wherein the historical promotion performance data employed to generate the promotion performance models comprises one or more of a type of promotion, a merchant category, a discount level, the accepted value of the promotion, a date range associated with the promotion, a number of impressions received for the promotion, a number of promotions offered, a redemption rate of the promotion, and a refund rate of the promotion;

generate a revenue equation using the demand model and the margin model based on a user-specified set of promotion values, wherein the revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the demand model and the margin model,

wherein the generation of the revenue equation comprises;

determining a set of potential promotion parameters including at least a minimum value and maximum value for each promotion parameter based on the historical promotion performance data, and identifying input values within a predefined number of standard deviations of the means of given combinations of promotion parameters;

determine an estimated revenue derived by the promotion and marketing service from predicted sales of the promotion using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation;

select at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue, wherein the selected at least one of the input sets of promotion pricing parameters comprise a selected promotion margin received by the promotion and marketing service for sales of the promotion; and

provide the selected at least one of the input sets of promotion pricing parameters to a merchant via a merchant interface;

receive an indication of a merchant selection of one or more of the selected at least one of the input sets; and

generate the promotion using the selected at least one of the input sets of promotion pricing parameters in response to receiving the indication;

monitor one or more performance characteristics of the promotion;

add the one or more performance characteristics of the promotion to the historical promotion performance data; and

update at least one of the demand model and the margin model based on the one or more performance characteristics of the promotion,

wherein the regression analysis is calculated in accordance with;

log q=α

₁ log p+α

₂ log d+α

₃c+α

₄sc+α

₅ds+α

₆di+α

₇r+α

₈

wherein each of the values are constants weights to be derived via the regression analysis, p is a unit price, d is the discount c is a category, sc is a subcategory, ds is a promotion service category, di is a division, and r is a merchant quality score, and

wherein for a given merchant, the category, subcategory, division, promotion service category, and merchant quality score is known and fixed, particular portions of an equation to predict promotion size are constant, and after accounting for the fixed factors, the size of a particular promotion is calculated by;

log q=α

₁ log p+α

₂ log d+α

₀

wherein α

₀ is a constant representing the fixed values for the particular promotion.

13. The apparatus of claim 12, wherein the historical promotion performance data comprises promotion parameters used for past promotions and performance characteristics of the past promotions.

14. The apparatus of claim 13, wherein the performance characteristics comprise at least one of a promotion redemption rate, a promotion size, or a promotion refund rate.

15. The apparatus of claim 12, wherein the promotion parameters comprise at least one of a promotion accepted value, a promotion promotional value, a promotion residual value, or a merchant category.

16. The apparatus of claim 12, wherein the revenue equation is generated using the demand model and the margin model, and wherein the estimated revenue is calculated by multiplying a promotion size derived from the demand model by the margin value derived from the margin model.

17. The apparatus of claim 16, wherein the margin model is employed to determine the margin value that results in at least a threshold merchant ROI for a merchant associated with the promotion.

18. The apparatus of claim 17, wherein the threshold merchant ROI is zero.

19. The apparatus of claim 12, wherein the one or more input sets of promotion pricing parameters are selected to maximize the estimated revenue.

20. The apparatus of claim 12, wherein the apparatus is further configured to generate a promotion using at least one of the one or more input sets of promotion pricing parameters.

21. The apparatus of claim 12, wherein the selected input set of promotion pricing parameters comprise a margin value, and wherein the apparatus is further configured to:

determine a promotion cost based on the margin value; and

present the promotion cost to a merchant for approval.

22. The apparatus of claim 21, wherein the apparatus is further configured to receive approval of the promotion cost and, in response to receiving the approval, generate the promotion with the selected input set of promotion pricing parameters.

23. A computer program product for providing, via a merchant interface, one or more dynamically updated pricing parameters for a promotion and performing continued analysis of promotion performance data for the promotions with established pricing parameters, resulting in a positive feedback loop by which predictive models are continually refined and improved to provide even more accurate predictions of optimal pricing parameters, the method comprising:

generate a demand model to determine the impact of various promotion parameters on the size of past promotion offerings, based on historical promotion performance data, the historical promotion performance data retrieved or received from a historical promotion performance database, wherein the demand model is generated by a regression analysis of the historical promotion performance data, the regression analysis providing a model for predicting a promotion size based on various promotion parameters, wherein the regression analysis is employed to ascertain the correlations between particular parameters and promotion size;

generate a margin model to determine a margin for a first entity for each sale of the promotion, the margin being a portion of an accepted value received by the first entity, that ensures both (i) at least a minimum ROI for the merchant, such that when the promotion is redeemed by a consumer towards the purchase of particular goods, services or experiences offered by the merchant, the merchant receives the minimum ROI from the first entity to account for at least the portion of a price of the particular goods, services or experiences provided to the consumer, while concurrently (ii) establishing that a minimum amount of revenue, in total, is generated by a sale of the promotion,

wherein the margin model is generated by examining the merchant ROI for past promotions with various parameters, and calculating a maximum margin available to the first entity to ensure the minimum ROI,

each of the demand model and the margin model configured to assist with selection of promotion pricing parameters, to determine promotion pricing parameters, or generate promotions with the determined pricing parameters,

wherein generation of the demand model and the margin model comprises

performing a regression analysis to determine an impact of each of one or more promotion parameters,

wherein promotion parameters comprise promotion pricing parameters, wherein each of the one or more predictive models are a result of machine learning algorithms that use the historical promotion performance data as a training set,

wherein the historical promotion performance data employed to generate the promotion performance models comprises one or more of a type of promotion, a merchant category, a discount level, the accepted value of the promotion, a date range associated with the promotion, a number of impressions received for the promotion, a number of promotions offered, a redemption rate of the promotion, and a refund rate of the promotion;

generate a revenue equation using the demand model and the margin model based on a user-specified set of promotion values, wherein the revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the demand model and the margin model,

wherein the generation of the revenue equation comprises;

determining a set of potential promotion parameters including at least a minimum value and maximum value for each promotion parameter based on the historical promotion performance data, and identifying input values within a predefined number of standard deviations of the means of given combinations of promotion parameters;

determine an estimated revenue derived by the promotion and marketing service from predicted sales of the promotion using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation;

select at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue, wherein the selected at least one of the input sets of promotion pricing parameters comprise a selected promotion margin received by the promotion and marketing service for sales of the promotion; and

provide the selected at least one of the input sets of promotion pricing parameters to a merchant via a merchant interface;

receive an indication of a merchant selection of one or more of the selected at least one of the input sets; and

generate the promotion using the selected at least one of the input sets of promotion pricing parameters in response to receiving the indication;

monitor one or more performance characteristics of the promotion;

add the one or more performance characteristics of the promotion to the historical promotion performance data; and

update at least one of the demand model and the margin model based on the one or more performance characteristics of the promotion,

wherein the regression analysis is calculated in accordance with;

log q=α

₁ log p+α

₂ log d+α

₃c+α

₄sc+α

₅ds+α

₆di+α

₇r+α

₈

wherein each of the values are constants weights to be derived via the regression analysis, p is a unit price, d is the discount c is a category, sc is a subcategory, ds is a promotion service category, di is a division, and r is a merchant quality score, and

wherein for a given merchant, the category, subcategory, division, promotion service category, and merchant quality score is known and fixed, particular portions of an equation to predict promotion size are constant, and after accounting for the fixed factors, the size of a particular promotion is calculated by;

log q=α

₁ log p+α

₂ log d+α

₀

wherein α

₀ is a constant representing the fixed values for the particular promotion.

24. The computer program product of claim 23, wherein the historical promotion performance data comprises promotion parameters used for past promotions and performance characteristics of the past promotions.

25. The computer program product of claim 24, wherein the performance characteristics comprise at least one of a promotion redemption rate, a promotion size, or a promotion refund rate.

26. The computer program product of claim 23, wherein the promotion parameters comprise at least one of a promotion accepted value, a promotion promotional value, a promotion residual value, or a merchant category.

27. The computer program product of claim 23, wherein the revenue equation is generated using the demand model and the margin model, and wherein the estimated revenue is calculated by multiplying a promotion size derived from the demand model by the margin value derived from the margin model.

28. The computer program product of claim 27, wherein the margin model is employed to determine the margin value that results in at least a threshold merchant ROI for a merchant associated with the promotion.

29. The computer program product of claim 28, wherein the threshold merchant ROI is zero.

30. The computer program product of claim 23, wherein the one or more input sets of promotion pricing parameters are selected to maximize the estimated revenue.

31. The computer program product of claim 23, wherein the computer program product further comprises instructions to configure the apparatus to generate a promotion using at least one of the one or more input sets of promotion pricing parameters.

32. The computer program product of claim 23, wherein the selected input set of promotion pricing parameters comprise a margin value, and wherein the apparatus is further configured to:

determine a promotion cost based on the margin value; and

present the promotion cost to a merchant for approval.

33. The computer program product of claim 32, wherein the computer program code further causes the apparatus to receive approval of the promotion cost and, in response to receiving the approval, generate the promotion with the selected input set of promotion pricing parameters.

34. A method for providing, via a merchant interface, one or more dynamically updated pricing parameters for a promotion and performing continued analysis of promotion performance data for the promotions with established pricing parameters, resulting in a positive feedback loop by which predictive models are continually refined and improved to provide even more accurate predictions of optimal pricing parameters, the method comprising:

generating a demand model to determine the impact of various promotion parameters on the size of past promotion offerings, based on historical promotion performance data, the historical promotion performance data retrieved or received from a historical promotion performance database, wherein the demand model is generated by a regression analysis of the historical promotion performance data, the regression analysis providing a model for predicting a promotion size based on various promotion parameters, wherein the regression analysis is employed to ascertain the correlations between particular parameters and promotion size;

generating a margin model to determine a margin for a first entity for each sale of the promotion, the margin being a portion of an accepted value received by the first entity, that ensures both (i) at least a minimum ROI for the merchant, such that when the promotion is redeemed by a consumer towards the purchase of particular goods, services or experiences offered by the merchant, the merchant receives the minimum ROI from the first entity to account for at least the portion of a price of the particular goods, services or experiences provided to the consumer, while concurrently (ii) establishing that a minimum amount of revenue, in total, is generated by a sale of the promotion,

wherein the margin model is generated by examining the merchant ROI for past promotions with various parameters, and calculating a maximum margin available to the first entity to ensure the minimum ROI,

each of the demand model and the margin model configured to assist with selection of promotion pricing parameters, to determine promotion pricing parameters, or generate promotions with the determined pricing parameters,

wherein generation of the demand model and the margin model comprises

performing a regression analysis to determine an impact of each of one or more promotion parameters,

wherein promotion parameters comprise promotion pricing parameters, wherein each of the one or more predictive models are a result of machine learning algorithms that use the historical promotion performance data as a training set,

wherein the historical promotion performance data employed to generate the promotion performance models comprises one or more of a type of promotion, a merchant category, a discount level, the accepted value of the promotion, a date range associated with the promotion, a number of impressions received for the promotion, a number of promotions offered, a redemption rate of the promotion, and a refund rate of the promotion;

generating a revenue equation using the demand model and the margin model based on a user-specified set of promotion values, wherein the revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the demand model and the margin model,

wherein the generation of the revenue equation comprises;

determining a set of potential promotion parameters including at least a minimum value and maximum value for each promotion parameter based on the historical promotion performance data, and identifying input values within a predefined number of standard deviations of the means of given combinations of promotion parameters;

determining, using a processor, an estimated revenue derived by the promotion and marketing service from predicted sales of the promotion using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation;

selecting at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue, wherein the selected at least one of the input sets of promotion pricing parameters comprise a selected promotion margin received by the promotion and marketing service for sales of the promotion; and

providing the selected at least one of the input sets of promotion pricing parameters to a merchant via a merchant interface;

receiving an indication of a merchant selection of one or more of the selected at least one of the input sets; and

generating the promotion using the selected at least one of the input sets of promotion pricing parameters in response to receiving the indication;

monitoring one or more performance characteristics of the promotion;

adding the one or more performance characteristics of the promotion to the historical promotion performance data; and

updating at least one of the demand model and the margin model based on the one or more performance characteristics of the promotion,

wherein the regression analysis is calculated in accordance with;

log q=α

₁ log p+α

₂ log d+α

₃c+α

₄sc+α

₅ds+α

₆di+α

₇r+α

₈

wherein each of the values are constants weights to be derived via the regression analysis, p is a unit price, d is the discount c is a category, sc is a subcategory, ds is a promotion service category, di is a division, and r is a merchant quality score, and

wherein for a given merchant, the category, subcategory, division, promotion service category, and merchant quality score is known and fixed, particular portions of an equation to predict promotion size are constant, and after accounting for the fixed factors, the size of a particular promotion is calculated by;

log q=α

₁ log p+α

₂ log d+α

₀

wherein α

₀ is a constant representing the fixed values for the particular promotion.

35. The method of claim 34, wherein the minimum merchant return on investment is zero.

36. An apparatus for providing, via a merchant interface, one or more dynamically updated pricing parameters for a promotion and performing continued analysis of promotion performance data for the promotions with established pricing parameters, resulting in a positive feedback loop by which predictive models are continually refined and improved to provide even more accurate predictions of optimal pricing parameters, the method comprising:

generate a demand model to determine the impact of various promotion parameters on the size of past promotion offerings, based on historical promotion performance data, the historical promotion performance data retrieved or received from a historical promotion performance database, wherein the demand model is generated by a regression analysis of the historical promotion performance data, the regression analysis providing a model for predicting a promotion size based on various promotion parameters, wherein the regression analysis is employed to ascertain the correlations between particular parameters and promotion size;

generate a margin model to determine a margin for a first entity for each sale of the promotion, the margin being a portion of an accepted value received by the first entity, that ensures both (i) at least a minimum ROI for the merchant, such that when the promotion is redeemed by a consumer towards the purchase of particular goods, services or experiences offered by the merchant, the merchant receives the minimum ROI from the first entity to account for at least the portion of a price of the particular goods, services or experiences provided to the consumer, while concurrently (ii) establishing that a minimum amount of revenue, in total, is generated by a sale of the promotion,

wherein the margin model is generated by examining the merchant ROI for past promotions with various parameters, and calculating a maximum margin available to the first entity to ensure the minimum ROI,

each of the demand model and the margin model configured to assist with selection of promotion pricing parameters, to determine promotion pricing parameters, or generate promotions with the determined pricing parameters,

wherein generation of the demand model and the margin model comprises

performing a regression analysis to determine an impact of each of one or more promotion parameters,

wherein promotion parameters comprise promotion pricing parameters, wherein each of the one or more predictive models are a result of machine learning algorithms that use the historical promotion performance data as a training set,

wherein the historical promotion performance data employed to generate the promotion performance models comprises one or more of a type of promotion, a merchant category, a discount level, the accepted value of the promotion, a date range associated with the promotion, a number of impressions received for the promotion, a number of promotions offered, a redemption rate of the promotion, and a refund rate of the promotion;

generate a revenue equation using the demand model and the margin model based on a user-specified set of promotion values, wherein the revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the demand model and the margin model,

wherein the generation of the revenue equation comprises;

determining a set of potential promotion parameters including at least a minimum value and maximum value for each promotion parameter based on the historical promotion performance data, and identifying input values within a predefined number of standard deviations of the means of given combinations of promotion parameters;

determine an estimated revenue derived by the promotion and marketing service from predicted sales of the promotion using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation;

select at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue, wherein the selected at least one of the input sets of promotion pricing parameters comprise a selected promotion margin received by the promotion and marketing service for sales of the promotion; and

provide the selected at least one of the input sets of promotion pricing parameters to a merchant via a merchant interface;

receive an indication of a merchant selection of one or more of the selected at least one of the input sets; and

generate the promotion using the selected at least one of the input sets of promotion pricing parameters in response to receiving the indication;

monitor one or more performance characteristics of the promotion;

add the one or more performance characteristics of the promotion to the historical promotion performance data; and

update at least one of the demand model and the margin model based on the one or more performance characteristics of the promotion,

wherein the regression analysis is calculated in accordance with;

log q=α

₁ log p+α

₂ log d+α

₃c+α

₄sc+α

₅ds+α

₆di+α

₇r+α

₈

wherein each of the values are constants weights to be derived via the regression analysis, p is a unit price, d is the discount c is a category, sc is a subcategory, ds is a promotion service category, di is a division, and r is a merchant quality score, and

wherein for a given merchant, the category, subcategory, division, promotion service category, and merchant quality score is known and fixed, particular portions of an equation to predict promotion size are constant, and after accounting for the fixed factors, the size of a particular promotion is calculated by;

log q=α

₁ log p+α

₂ log d+α

₀

wherein α

₀ is a constant representing the fixed values for the particular promotion.

37. The apparatus of claim 36, wherein the minimum merchant return on investment is zero.

38. A computer program product for providing, via a merchant interface, one or more dynamically updated pricing parameters for a promotion and performing continued analysis of promotion performance data for the promotions with established pricing parameters, resulting in a positive feedback loop by which predictive models are continually refined and improved to provide even more accurate predictions of optimal pricing parameters, the method comprising:

generate a demand model to determine the impact of various promotion parameters on the size of past promotion offerings, based on historical promotion performance data, the historical promotion performance data retrieved or received from a historical promotion performance database, wherein the demand model is generated by a regression analysis of the historical promotion performance data, the regression analysis providing a model for predicting a promotion size based on various promotion parameters, wherein the regression analysis is employed to ascertain the correlations between particular parameters and promotion size;

generate a margin model to determine a margin for a first entity for each sale of the promotion, the margin being a portion of an accepted value received by the first entity, that ensures both (i) at least a minimum ROI for the merchant, such that when the promotion is redeemed by a consumer towards the purchase of particular goods, services or experiences offered by the merchant, the merchant receives the minimum ROI from the first entity to account for at least the portion of a price of the particular goods, services or experiences provided to the consumer, while concurrently (ii) establishing that a minimum amount of revenue, in total, is generated by a sale of the promotion,

wherein the margin model is generated by examining the merchant ROI for past promotions with various parameters, and calculating a maximum margin available to the first entity to ensure the minimum ROI,

each of the demand model and the margin model configured to assist with selection of promotion pricing parameters, to determine promotion pricing parameters, or generate promotions with the determined pricing parameters,

wherein generation of the demand model and the margin model comprises

performing a regression analysis to determine an impact of each of one or more promotion parameters,

wherein promotion parameters comprise promotion pricing parameters, wherein each of the one or more predictive models are a result of machine learning algorithms that use the historical promotion performance data as a training set,

wherein the historical promotion performance data employed to generate the promotion performance models comprises one or more of a type of promotion, a merchant category, a discount level, the accepted value of the promotion, a date range associated with the promotion, a number of impressions received for the promotion, a number of promotions offered, a redemption rate of the promotion, and a refund rate of the promotion;

generate a revenue equation using the demand model and the margin model based on a user-specified set of promotion values, wherein the revenue equation provides an estimate of a revenue received by the promotion and marketing service based on the demand model and the margin model,

wherein the generation of the revenue equation comprises;

determining a set of potential promotion parameters including at least a minimum value and maximum value for each promotion parameter based on the historical promotion performance data, and identifying input values within a predefined number of standard deviations of the means of given combinations of promotion parameters;

determine an estimated revenue derived by the promotion and marketing service from predicted sales of the promotion using the revenue equation based on one or more input sets of promotion pricing parameters provided as input to the revenue equation;

select at least one of the input sets of promotion pricing parameters for the promotion based on the estimated revenue, wherein the selected at least one of the input sets of promotion pricing parameters comprise a selected promotion margin received by the promotion and marketing service for sales of the promotion; and

provide the selected at least one of the input sets of promotion pricing parameters to a merchant via a merchant interface;

receive an indication of a merchant selection of one or more of the selected at least one of the input sets; and

generate the promotion using the selected at least one of the input sets of promotion pricing parameters in response to receiving the indication;

monitor one or more performance characteristics of the promotion;

add the one or more performance characteristics of the promotion to the historical promotion performance data; and

update at least one of the demand model and the margin model based on the one or more performance characteristics of the promotion,

wherein the regression analysis is calculated in accordance with;

log q=α

₁ log p+α

₂ log d+α

₃c+α

₄sc+α

₅ds+α

₆di+α

₇r+α

₈

wherein each of the values are constants weights to be derived via the regression analysis, p is a unit price, d is the discount c is a category, sc is a subcategory, ds is a promotion service category, di is a division, and r is a merchant quality score, and

wherein for a given merchant, the category, subcategory, division, promotion service category, and merchant quality score is known and fixed, particular portions of an equation to predict promotion size are constant, and after accounting for the fixed factors, the size of a particular promotion is calculated by;

log q=α

₁ log p+α

₂ log d+α

₀

wherein α

₀ is a constant representing the fixed values for the particular promotion.

39. The computer program product apparatus of claim 38, wherein the minimum merchant return on investment is zero.