System for display advertising optimization using click or conversion performance

1. An advertisement impression distribution system, comprising:

a data processing system comprising one or more processors and data memory, the data processing system operable to generate an allocation plan for serving advertisement impressions, the allocation plan to allocate a first portion of advertisement impressions to satisfy guaranteed demand and a second portion of advertisement impressions to satisfy non-guaranteed demand;

where the data processing system includes an optimizer component to establish a relationship between the first portion of advertisement impressions and the second portion of advertisement impressions, the relationship defining a range of possible proportions of allocation of the first portion of advertisement impressions and the second portion of advertisement impressions;

where the optimizer generates a solution in accordance with maximizing guaranteed demand fairness, non-guaranteed demand revenue, and click value, where the click value comprises the product of a probability of a click occurring when the advertisement is served and a value of the click to the guaranteed demand, and where the solution identifies a determined proportion of the first portion of advertisement impressions to serve and a determined proportion of the second portion of advertisement impressions to serve; and

where the data processing system outputs the allocation plan including the solution to control serving of the advertisement impressions in the determined proportions.

2. The advertisement impression distribution system of claim 1 , where the value of the click to the guaranteed demand is set to a value selected from the group consisting of one, an importance level, and an actual monetary value.

3. The advertisement impression distribution system of claim 1 , where the data processing system first optimizes a weighted sum of both the click value and non-guaranteed demand revenue, and then optimizes guaranteed demand fairness.

4. The advertisement impression distribution system of claim 3 , where the optimization is subject to a determined fraction of the guaranteed demand fairness.

5. The advertisement impression distribution system of claim 1 , where the data processing system first optimizes the click value and then optimizes a weighted sum of both the guaranteed demand fairness and the non-guaranteed demand revenue.

6. The advertisement impression distribution system of claim 5 , where the optimization is subject to a determined fraction of the click or conversion value.

7. The advertisement impression distribution system of claim 1 , where the data processing system first optimizes the non-guaranteed demand revenue and then optimizes a weighted sum of both the guaranteed demand fairness and the click value.

8. The advertisement impression distribution system of claim 7 , where the optimization is subject to a bound on the non-guaranteed demand revenue.

9. The advertisement impression distribution system of claim 1 , where the guaranteed demand fairness, the click value, and the non-guaranteed demand revenue are optimized in succession.

10. The advertisement impression distribution system of claim 1 , where the advertisement impressions comprise online graphical advertisements in a unified marketplace for graphical advertisement impressions.

11. The advertisement impression distribution system of claim 1 , where click value comprises a probability of a conversion of a sale in accordance with the advertisement impression being viewed.

12. The advertisement impression distribution system of claim 1 , where the click value comprises a probability that an advertisement is of interest to a user viewing the advertisement impression.

13. A method for distribution of advertisement impressions in a network, comprising:

generating, with a computing system, an allocation plan for serving advertisement impressions over the network, the allocation plan to allocate a first portion advertisement impressions to satisfy guaranteed demand and a second portion of advertisement impressions to satisfy non-guaranteed demand;

establishing, with the computing system, a relationship between the first portion of advertisement impressions and the second portion of advertisement impressions, the relationship defining a range of possible proportions of allocation of the first portion of advertisement impressions and the second portion of advertisement impressions;

generating, with the computing system, a solution in accordance with maximizing guaranteed demand fairness, non-guaranteed demand revenue, and click value, where the click value comprises the product of a probability of a click occurring when the advertisement is served and a value of the click to the guaranteed demand, and where the solution identifies a determined proportion of the first portion of advertisement impressions to serve and a determined proportion of the second portion of advertisement impressions to serve; and

outputting, with the computing system, the allocation plan including the solution to control serving of the advertisement impressions in the determined proportions.

14. The method of claim 13 , where the value of the click is set to a value selected from the group consisting of one, an importance level, and an actual monetary value.

15. The method of claim 13 , further comprising first optimizing a weighted sum of both the click value and non-guaranteed demand revenue, and then optimizing guaranteed demand fairness.

16. The method of claim 13 , further comprising first optimizing the click value and then optimizing a weighted sum of both the guaranteed demand fairness and non-guaranteed demand revenue.

17. The method of claim 13 , further comprising first optimizing the non-guaranteed demand revenue and then optimizing a weighted sum of both the guaranteed demand fairness and the click or conversion value.

18. The method of claim 13 , further comprising optimizing the guaranteed demand fairness, the click or conversion value, and the non-guaranteed demand revenue in succession.

19. The method claim 13 , where the advertisement impressions comprise online graphical advertisements in a unified marketplace for graphical advertisement impressions.

20. The method of claim 13 , where click value comprises a probability of a conversion of a sale in accordance with the advertisement impression being viewed.

21. The method of claim 13 , where the click value further comprises a probability that an advertisement is relevant to a user viewing the advertisement impression.