System and method for a data driven meta-auction mechanism for sponsored search

• US 8,260,680 B2
• Filed: 12/18/2008
• Issued: 09/04/2012
• Est. Priority Date: 12/18/2008
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Tomak, Kerem
• Primary Examiner(s): VEZERIS, JAMES A
• Application Number:
  US12/338,460
• Publication Number:
  US 20100161438A1
• Time in Patent Office: 1,356 Days
• Field of Search: 705/26, 705/35
• US Class Current: 705/26.3
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/08 Auctions

Abstract

Apparatuses, methods, and systems directed to deriving optimal parameters of a learning algorithm to maximize an objective function of online keyword auctions for bidded terms. Some embodiments of the invention simulate online keyword auctions based on historical data for the bidded terms, wherein the parameters of the simulated auctions such as market reserve prices of the bidded terms are determined by an adaptive learning algorithm. The values of the parameters of the learning algorithm are optimized by a stochastic optimization method to maximize an objective function for the auctions of the bidded terms.

Claims

1. A method implemented in a computer system having at least one processor, storage, and a communication platform, comprising:

performing by the at least one processor the steps of;

accessing an adaptive learning algorithm to maximize an objective function for online keyword auctions of one or more bidded terms each comprising one or more keywords, wherein the adaptive learning algorithm comprises one or more learning parameters, and each online keyword auction comprises one or more auction parameters; and

determining optimal values of the one or more learning parameters of the adaptive learning algorithm, including

changing values of the one or more learning parameters of the adaptive learning algorithm using a stochastic optimization method,

simulating one or more online keyword auctions,

calculating values of the objective function based on results of the one or more simulated online keyword auctions,

determining the optimal values of the one or more learning parameters that maximize the objective function, and

storing the determined optimal values of the one or more learning parameters of the adaptive learning algorithm in a data store.

2. The method of claim 1, wherein the simulating step comprises:

assigning values to the one or more auction parameters, the values being chosen by the adaptive learning algorithm,

generating one or more bidders and bids for each online keyword auction based on historical data without making assumptions of the bidders, and

deciding the results of the one or more simulated auctions based on the one or more auction parameters and behavior of the generated bidders, wherein the behavior is derived from the historical data.

3. The method of claim 1, wherein the one or more auction parameters comprise a market reserve price of a bidded term.

4. The method of claim 2, wherein the historical data comprises information related to past auctions of a bidded term, the information comprising market reserve prices of the bidded term, a number of bidders and their bids, a duration of the auctions, and winning bids.

5. The method of claim 1, wherein the adaptive learning algorithm comprises a softmax action selection process.

6. The method of claim 1, wherein the stochastic optimization method comprises a simultaneous perturbation stochastic approximation process.

7. The method of claim 1, wherein in the simulating step, a behavior of a bidder for a bidded term comprises a range of values of the bidder'"'"'s valuation of the bidded term and a range of values of the bidder'"'"'s loss aversion.

8. The method of claim 1, wherein the objective function comprises an overall estimated revenue from winning bids of the one or more bidded terms in a period of time.

9. An apparatus, comprising:

at least one processor; and

a memory configured to store logic that, when executed by the at least on processor, causes the at least one processor to perform the steps of;

accessing access an adaptive learning algorithm to maximize an objective function for online keyword auctions of one or more bidded terms each comprising one or more keywords, wherein the adaptive learning algorithm comprises one or more learning parameters, and the online keyword auctions comprise one or more auction parameters; and

determining optimal values of the one or more learning parameters of the adaptive learning algorithm, including

changing values of the one or more learning parameters of the adaptive learning algorithm using a stochastic optimization method,

simulating one or more online keyword auctions,

calculating values of the objective function based on results of the one or more simulated online keyword auctions, and

determining the optimal values of the one or more learning parameters that maximize the objective function.