Abstract: A computer-implemented automated decision support system for designing an auction for a given item includes a structure extractor that estimates unknown elements of market structure of the auction based on auction characteristics data extracted from historical auctions for similar items and a bidding model matching the extracted auction characteristics data. The decision support system also includes a bidding behavior predictor that predicts bidding behaviors of bidders in the auction based on the estimated unknown elements of market structure and characteristics of the auction. In addition, the system includes an optimizer that employs an evaluation criterion to generate an evaluation of the auction based on (1) the estimated unknown elements of market structure and (2) the predicted bidding behavior of bidders. A method of providing an automated auction analysis is also described.

Abstract: An automated estimation and optimization solution for selecting the best auction format by determining the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements. Structural analysis of bid data from prior auctions is used to identify and estimate the distributions of bidders' private signals conditional on observable bidder characteristics. The estimated signal distributions, identified by the structural analysis, are used to evaluate alternative auction formats and to select the best format from among a given set of candidates. The present invention provides decision support tools to select an auction format based on structural econometric analysis of available data on the market environment. A decision-maker may estimate the unobservable private signals of the bidders and to determine the best auction format the decision maker can employ to sell a given set of items.

Abstract: The present invention provides an automated estimation and optimization solution for selecting the optimal bid for an item in an auction. The characteristics of the auction are selected (e.g., auction format, reserve price). A relevant bidding model, based on the characteristics of the auction, is selected. The structure of the auction is estimated based on the relevant bidding model. A bid function is determined based on the auction structure and user inputs regarding the item being bid on and the characteristics of the rival bidders. An optimal bid is determined based on the bid function and user-defined evaluation criterion. An embodiment of the present invention provides a method and system that determines the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements.

Abstract: One embodiment of the present invention provides a method and system that computes the optimal level of the reserve price for an auction, with respect to a multiplicity of possible evaluation criteria that the end user of the system may specify. In one embodiment, structural elements characterizing the auction situation are estimated from bid data available on past auctions. The estimated structural elements are then used in the formulation of the user's expected payoff as a function of the reserve price. This objective function is then optimized to obtain the best level of the reserve price. In one embodiment, this method is implemented by a process executed on a computer system, under the control of software and firmware directing the operation of its processors and components. In one embodiment, a computer readable medium causes a computer system to execute the steps in a process for implementing the method.

Abstract: One embodiment of the present invention provides a method and system that determines the optimal preference policy for a market, such as an auction, with respect to a multiplicity of possible evaluation criteria that auction participants or other end users specify. In one embodiment, a method and system that configures the optimal preference policies that can be implemented in any market, particularly an auction, applicable to any auction format a market decision maker may wish to conduct. An embodiment of the present invention estimates bidders' private information and correspondingly identifies exploitable asymmetries to implement a preferential treatment policy. In one embodiment, this method is implemented on a computer system, under the control of software and firmware directing the operation of its processor and other components. In one embodiment, a computer readable medium causes a computer system to execute the method.

Abstract: A method and apparatus for determining private information and risk attitudes of bidders at auctions. By varying auction formats, the underlying risk attitudes and joint distribution of bidders' private information is extracted. Bids submitted in utility-independent auctions are used to determine the bidders private information. Risk attitudes for bidders are determined using utility-dependent auctions and using the determined bidders' private information. When there is insufficient auction data for determining private information and risk attitudes, additional auctions are conducted to obtain the needed auction data. The results can then be used for designing auctions and for determining bids to be made by buyers.

Abstract: A method for action selection based upon an objective of an outcome relative to a subject. In one embodiment, a training set is obtained that contains attributes of a subject. In the present embodiment, a best behavioral model for predicting an outcome when a subject has an action applied is calculated. The training set is mapped to the best behavioral model. The mapping provides a base from which a random sub-sample is acquired. In the present embodiment, a random sub-sample of the training set and the best behavioral model is then selected. This random sub-sample reduces the computational requirements when determining an optimized strategy. The optimized strategy provides an optimal action relative to the subject for the objective of the outcome. In one embodiment, the subject is a customer of a business entity, enabled to interact with the customer, and an action is a promotion offered by the business entity.

Abstract: A method for generating a demand estimate for a product includes gathering a set of auction data which is relevant to the product, removing from the auction data all but a highest bid from each unique bidder in the auction data, and correcting a bias in the auction data caused by a set of characteristics of an auction from which the auction data is obtained. In one embodiment, the auction data is obtained from an on-line auction which is characterized by bidders not necessarily knowing the start time of the auction.

Abstract: An apparatus and a method for extracting an underlying demand system for optimal product bundling and design. User input is received that indicates items for which a demand system is to be determined. Auction participants are selected. The structure of the auction is configured for determining demand complementarities of the items to be auctioned. At least one auction is then conducted using the configured structure so as to obtain bid data for each of the items that are auctioned. The bid data is then analyzed to determine an estimate of a demand system for the products.

Abstract: The present invention provides an automated estimation and optimization solution for selecting the optimal bid for an item in an auction. The characteristics of the auction are selected (e.g., auction format, reserve price). A relevant bidding model, based on the characteristics of the auction, is selected. The structure of the auction is estimated based on the relevant bidding model. A bid function is determined based on the auction structure and user inputs regarding the item being bid on and the characteristics of the rival bidders. An optimal bid is determined based on the bid function and user-defined evaluation criterion. An embodiment of the present invention provides a method and system that determines the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements.

Abstract: One embodiment of the present invention provides a method and system that computes the optimal level of the reserve price for an auction, with respect to a multiplicity of possible evaluation criteria that the end user of the system may specify. In one embodiment, structural elements characterizing the auction situation are estimated from bid data available on past auctions. The estimated structural elements are then used in the formulation of the user's expected payoff as a function of the reserve price. This objective function is then optimized to obtain the best level of the reserve price. In one embodiment, this method is implemented by a process executed on a computer system, under the control of software and firmware directing the operation of its processors and components. In one embodiment, a computer readable medium causes a computer system to execute the steps in a process for implementing the method.

Abstract: The present invention provides an automated estimation and optimization solution for selecting the best auction format. An embodiment of the present invention provides a method and system that determines the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements. In one embodiment of the present invention, structural analysis of bid data from prior auctions is used to identify and estimate the distributions of bidders' private signals conditional on observable bidder characteristics. In one embodiment, the estimated signal distributions, identified by the structural analysis, are used to evaluate alternative auction formats and to select the best format from among a given set of candidates. In one embodiment, the present invention provides decision support tools to select an auction format based on structural econometric analysis of available data on the market environment.

Abstract: One embodiment of the present invention provides a method and system that determines the optimal preference policy for a market, such as an auction, with respect to a multiplicity of possible evaluation criteria that auction participants or other end users specify. In one embodiment, a method and system that configures the optimal preference policies that can be implemented in any market, particularly an auction, applicable to any auction format a market decision maker may wish to conduct. An embodiment of the present invention estimates bidders' private information and correspondingly identifies exploitable asymmetries to implement a preferential treatment policy. In one embodiment, this method is implemented on a computer system, under the control of software and firmware directing the operation of its processor and other components. In one embodiment, a computer readable medium causes a computer system to execute the method.

Abstract: A method and apparatus for determining private information and risk attitudes of bidders at auctions. By varying auction formats, the underlying risk attitudes and joint distribution of bidders' private information is extracted. Bids submitted in utility-independent auctions are used to determine the bidders private information. Risk attitudes for bidders are determined using utility-dependent auctions and using the determined bidders' private information. When there is insufficient auction data for determining private information and risk attitudes, additional auctions are conducted to obtain the needed auction data. The results can then be used for designing auctions and for determining bids to be made by buyers.

Abstract: A method for action selection based upon an objective of an outcome relative to a subject. In one embodiment, a training set is obtained that contains attributes of a subject. In the present embodiment, a best behavioral model for predicting an outcome when a subject has an action applied is calculated. The training set is mapped to the best behavioral model. The mapping provides a base from which a random sub-sample is acquired. In the present embodiment, a random sub-sample of the training set and the best behavioral model is then selected. This random sub-sample reduces the computational requirements when determining an optimized strategy. The optimized strategy provides an optimal action relative to the subject for the objective of the outcome. In one embodiment, the subject is a customer of a business entity, enabled to interact with the customer, and an action is a promotion offered by the business entity.

Abstract: A computer-implemented automated decision support system for designing an auction for a given item includes a structure extractor that estimates unknown elements of market structure of the auction based on auction characteristics data extracted from historical auctions for similar items and a bidding model matching the extracted auction characteristics data. The decision support system also includes a bidding behavior predictor that predicts bidding behaviors of bidders in the auction based on the estimated unknown elements of market structure and characteristics of the auction. In addition, the system includes an optimizer that employs an evaluation criterion to generate an evaluation of the auction based on (1) the estimated unknown elements of market structure and (2) the predicted bidding behavior of bidders. A method of providing an automated auction analysis is also described.

Abstract: A method and system for predicting the class membership of a record where information for one or more variables in the record is missing. Multiple classification trees are generated. A first classification tree is computed using a substantially complete set of information for all of the variables. Other classification trees are computed for different subsets of the variables. Variables are selected for inclusion in a subset based on how strongly they influence the prediction of class membership. The first classification tree (based on the substantially complete set of information) is applied to a record with missing information. If missing information is needed by this tree in order to classify the record, another classification tree that is not based on the missing variable is selected. The class membership for a record with information missing is predicted more accurately without substantially increasing the complexity of the prediction.

Abstract: A method for generating a demand estimate for a product includes gathering a set of auction data which is relevant to the product, removing from the auction data all but a highest bid from each unique bidder in the auction data, and correcting a bias in the auction data caused by a set of characteristics of an auction from which the auction data is obtained. In one embodiment, the auction data is obtained from an on-line auction which is characterized by bidders not necessarily knowing the start time of the auction.