System and method for pricing advertisement placements online in a real-time bidding environment

• US 9,715,699 B1
• Filed: 04/04/2013
• Issued: 07/25/2017
• Est. Priority Date: 04/06/2012
• Status: Active Grant

• Current Assignee: Valassis Digital Corp. (MX Holdings One LLC)
• Original Assignee: MaxPoint Interactive (MX Holdings One LLC)
• Inventors: Els, Michael, Postelnik, Igor
• Primary Examiner(s): STOLTENBERG, DAVID J
• Application Number:
  US13/857,123
• Time in Patent Office: 1,573 Days
• 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
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0275 Auctions

Abstract

A method and system for pricing advertisement placements online in a real-time bidding (RTB) environment is disclosed. According to one embodiment, a computer-implemented method includes receiving a plurality of responses from a plurality of real-time bidding (RTB) requests for an advertisement placement and determining a first data set from the plurality of responses, where the first data set includes prices paid for winning the advertisement placement. The computer-implemented method further includes determining a second data set from the plurality of responses, where the second data set includes losing bid prices, and estimating a price distribution curve based on one or more of the first data set and the second data set.

Claims

1. A computer-implemented method for automated pricing evaluation for a particular online placement and real-time bidding control based on the automated pricing evaluation in an automated real-time bidding (RTB) environment, the method comprising:

receiving, at an RTB bidding system, from an RTB exchange, a series of bid requests for the particular online placement, each bid request identifying the particular online placement in network-based digital content being loaded or rendered by a respective internet-connected device;

for each of a plurality of the received bid requests for the particular online placement, determining by the RTB bidding system (a) to submit a bid to the RTB exchange for the particular online placement and (b) a bid price for the bid;

wherein each bid submitted by the RTB bidding system is included in an auction for the online placement identified in the respective bid request and, via the auction, results in a winning bid or a losing bid;

wherein the RTB exchange implements a second price auction, such that;

for each of a plurality of winning bids submitted by the RTB bidding system for the particular online placement, the RTB bidding system is informed of a price paid by the RTB bidding system for the particular online placement, as determined by the RTB exchange;

for each of a plurality of losing bids submitted by the RTB bidding system for the particular online placement, the RTB bidding system is not informed of the price paid for the particular online placement;

collecting, by the RTB bidding system, a first data set including the respective price paid for the particular online placement for each of the plurality of winning bids submitted by the RTB bidding system for the particular online placement, wherein for at least some winning bids the respective price paid is lower than the bid price of the winning bid;

collecting, by the RTB bidding system, a right-censored second data set including the losing bid price submitted by the RTB bidding system for each of the plurality of losing bids submitted by the RTB bidding system for the particular online placement, the losing bid prices defining right-censored data points;

calculating an estimated market price distribution curve for the particular online placement based on the first data set and the second data set by;

selecting a statistical model representing an actual market price distribution for the second price auction implemented by the RTB exchange, the statistical model accounting for right-censored data;

fitting the model to the first data set and the right-censored second data set to generate an estimated market price distribution curve for the particular online placement, the estimated market price distribution curve representing a distribution of prices paid for the particular online placement by a market of bidders of over time;

subsequently receiving, at the RTB bidding system, at least one additional bid request for the particular online placement; and

for each received additional bid request, the RTB bidding system determining, based on the calculated estimated market price distribution curve, at least one of (a) whether to submit a bid for the additional bid request or (b) a bid price for the additional bid request.

2. The computer-implemented method of claim 1, further comprising calculating a parameter of the estimated market price distribution curve based on a likelihood function.

3. The computer-implemented method of claim 1, further comprising selecting the particular online placement from a plurality of advertisement placements, wherein the particular online placement has a performance score equal to or greater than a pacing threshold.

4. The computer-implemented method of claim 3, further comprising selecting a desired bid price for the particular online placement on the estimated market price distribution curve, wherein the desired bid price is based on maintaining the performance score equal to or greater than the pacing threshold.

5. The computer-implemented method of claim 2, further comprising contributing the second data set as right-censored data points to a survival function, wherein the survival function is part of the likelihood function.

6. The computer-implemented method of claim 2, further comprising contributing the first data set as uncensored data points to the likelihood function.

7. The computer-implemented method of claim 1, wherein the estimated market price distribution curve follows a parametric distribution.

8. The computer-implemented method of claim 1, wherein the estimated market price distribution curve follows a non-parametric distribution.

9. The computer-implemented method of claim 4, further comprising determining the performance score based on a number of impressions served and feedback data comprising clicks, online actions and sales data.

10. The computer-implemented method of claim 1, wherein in the second price auction implemented by the RTB exchange, in auctions for the particular online placement that include multiple bids having different bid prices, the price paid for the particular online placement is lower than the highest of the multiple bid prices.

21. The computer-implemented method of claim 1, wherein for at least some winning bids submitted by the RTB bidding system for the particular online placement, the price paid by the RTB bidding system for the particular online placement is defined by a next highest bid price submitted by another bidding system.

11. A non-transitory computer readable medium having stored thereon computer-readable instructions for automated pricing evaluation for a particular online placement and real-time bidding control based on the automated pricing evaluation in an automated real-time bidding (RTB) environment, and a processor coupled to the non-transitory computer readable medium, wherein the computer-readable instructions are executable by the processor to:

receive, at an RTB bidding system, from an RTB exchange, a series of bid requests for the particular online placement, each bid request identifying the particular online placement in network-based digital content being loaded or rendered by a respective internet-connected device;

for each of a plurality of the received bid requests for the particular online placement, determine, by the RTB bidding system (a) to submit a bid to the RTB exchange for the particular online placement and (b) a bid price for the bid;

wherein each bid submitted by the RTB bidding system is included in an auction for the online placement identified in the respective bid request and, via the auction, results in a winning bid or a losing bid;

wherein the RTB exchange implements a second price auction, such that;

for each of a plurality of winning bids submitted by the RTB bidding system for the particular online placement, the RTB bidding system is informed of a price paid by the RTB bidding system for the particular online placement, as determined by the RTB exchange;

for each of a plurality of losing bids submitted by the RTB bidding system for the particular online placement, the RTB bidding system is not informed of the price paid for the particular online placement;

collect, by the RTB bidding system, a first data set including the respective price paid for the particular online placement for each of the plurality of winning bids submitted by the RTB bidding system for the particular online placement;

collect, by the RTB bidding system, a right-censored second data set including the losing bid price submitted by the RTB bidding system for each of the plurality of losing bids submitted by the RTB bidding system for the particular online placement, the losing bid prices defining right-censored data points;

calculate an estimated market price distribution curve for the particular online placement based on the first data set and the second data set by;

selecting a statistical model representing an actual market price distribution for the second price auction implemented by the RTB exchange, the statistical model accounting for right-censored data;

fitting the model to the first data set and the right-censored second data set to generate an estimated market price distribution curve for the particular online placement, the estimated market price distribution curve representing a distribution of prices paid for the particular online placement by a market of bidders of over time;

subsequently receive, at the RTB bidding system, at least one additional bid request for the particular online placement; and

for each received additional bid request, determine, based on the calculated estimated market price distribution curve, at least one of (a) whether to submit a bid for the additional bid request or (b) a bid price for the additional bid request.

12. The non-transitory computer readable medium of claim 11, wherein the processor executes the instructions to calculate a parameter of the estimated market price distribution curve based on a likelihood function.

13. The non-transitory computer readable medium of claim 11, wherein the processor executes the instructions to select the particular online placement from a plurality of advertisement placements, wherein the particular online placement has a performance score equal to or greater than a pacing threshold.

14. The non-transitory computer readable medium of claim 13, wherein the processor executes the instructions to select a desired bid price for the particular online placement on the estimated market price distribution curve, wherein the desired bid price is based on maintaining the performance score equal to or greater than the pacing threshold.

15. The non-transitory computer readable medium of claim 12, wherein the processor executes the instructions to contribute the second data set as right-censored data points to a survival function, wherein the survival function is part of the likelihood function.

16. The non-transitory computer readable medium of claim 12, wherein the processor executes the instructions to contribute the first data set as uncensored data points to the likelihood function.

17. The non-transitory computer readable medium of claim 11, wherein the estimated market price distribution curve follows a parametric distribution.

18. The non-transitory computer readable medium of claim 11, wherein the estimated market price distribution curve follows a non-parametric distribution.

19. The non-transitory computer readable medium of claim 14, wherein the processor executes the instructions to determine the performance score based on a number of impressions served and feedback data comprising clicks, online actions and sales data.

20. The non-transitory computer readable medium of claim 11, wherein in the second price auction implemented by the RTB exchange, in auctions for the particular online placement that include multiple bids having different bid prices, the price paid for the particular online placement is lower than the highest of the multiple bid prices.