Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing decision systems. In some implementations, methods can include receiving a component request specifying a maximum number of digital components that are capable of being presented on a particular electronic document being rendered at a client device. A ranking score for the given digital component is determined based on a maximum interaction increase factor of formatting available to be applied to the given digital component, the current eligibility value, and the historical eligibility value data. The given digital component is ranked among other available digital components based on the determined ranking score. The given digital component is selected for distribution based on the ranking score of the given digital component being included in the maximum number of highest ranked digital components. The given digital component is transmitted to a client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing decision systems. In some implementations, methods can include receiving a component request specifying a maximum number of digital components that are capable of being presented on a particular electronic document being rendered at a client device. A ranking score for the given digital component is determined based on a maximum interaction increase factor of formatting available to be applied to the given digital component, the current eligibility value, and the historical eligibility value data. The given digital component is ranked among other available digital components based on the determined ranking score. The given digital component is selected for distribution based on the ranking score of the given digital component being included in the maximum number of highest ranked digital components. The given digital component is transmitted to a client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing machine learning systems. In one aspect a method includes determining an average error of a machine learning system (“MLS”). An evaluation function that provides a result that would have been achieved using a specified value of a given parameter is defined. An expected outcome function that provides expected results for prior events based on the error of the MLS is defined. For each of multiple prior events, a target value of the given parameter is determined, e.g., using the expected outcome function. A model is generated using the MLS based on features of the prior events and the determined target values of the given parameter for the prior events. A value is assigned to the given parameter for a new event based on application of the model to features of the new event.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing utilization of distribution parameters are disclosed. In one aspect, a method includes a restrictive distribution parameter that is different from any distribution parameters in a first set of distribution parameters. An acceptable peak bid for a second set of distribution parameters that includes the restrictive distribution parameter is determined based on a first bid for the first set of distribution parameters. A determination is made that a second bid received from the content item provider does not exceed the acceptable peak bid, and the second bid is associated with the second set of distribution parameters based on the determination.

Abstract: The present application relates to systems and computer-implemented methods for conducting a second price auction associated with an opportunity to realize an online advertisement. In some implementations, advertisers may be informed with the opportunity to realize the online advertisement, and may be provided with information associated with a user that may view the opportunity to realize the online advertisement; an individual reserve price may then be determined for each advertiser, based on the advertiser's individual bidding preference and the information associated with the user; and then the auction may be conducted to determine a winning bidder among candidate advertisers whose bidding price is higher than the individual reserve price associated therewith, using second price method.

Abstract: The present application relates to systems and computer-implemented methods for determining a future bidding strategy regarding auctions associated with realization of an online advertisement. In some implementations, a server may be used to determine an optimized bid pacing parameter for an online advertisement based on a current bid pacing parameter associated with the online advertisement and an online advertisement supply information for a time period so that based on the optimized bid pacing, realization of the online advertisement over the time period substantially confirms to a spending strategy associated with the online advertisement during the time period. As such, the systems and computer-implemented methods may allow advertisers to control their spending strategy accurately during an advertising campaign.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for increasing advertiser utility in broad match auctions. In one aspect, a method includes receiving, from an advertiser, a set of keywords; accessing a linear program for a keyword language auction; determining a solution to the linear program; determining, based on the solution to the linear program, a proper subset of the keywords that increases the advertiser's utility relative to the advertiser's utility for the set of keywords; and generating utility bids for each of the keywords in the subset, each utility bid corresponding to one of the keywords in the subset and being a bid price for the keywords.

Abstract: An item is allocated among two bidders that value the item very differently. The allocation is based on a probability that each of the bidders is allocated the item. The probability that each bidder is allocated the item is determined based on a non-linear function that is applied to bids that are received from the bidders. The item can be allocated semi-randomly subject to the probability that each bidder is allocated the item. A bidder can be required to pay its bid price only when allocated the item or each bidder can be required to pay an all-pay price regardless of which bidder is allocated the item. If the item is allocated in multiple auctions, the bidders can be ensured allocation of the item a minimum number of integer times based on the probabilities.