Abstract: A model is constructed for an initial subset of the data using a first parameter estimation algorithm. The model may be evaluated, for example, by applying the model to a holdout data set of the data. If the model is not acceptable, additional data is added to the data subset and the first parameter estimation algorithm is repeated for the aggregate data subset. An appropriate subset of the data exists when the first parameter estimation algorithm produces an acceptable model. The appropriate subset of the data may then be employed by a second parameter estimation algorithm, which may be a more accurate version of the first algorithm or a different algorithm altogether, to build a statistical model to characterize the data.

Abstract: The claimed subject matter relates to an architecture that can identify relevant features or characteristics of one or more shoppers in the vicinity of a business establishment. In addition, the architecture can monitor resources both of the business establishment as well as other remote or disparate businesses. Based upon the shopper traffic data and the resource data, the architecture can determine or infer a traffic modifier (e.g., an advertisement or incentive) that can be transmitted to a display device that is typically in close proximity to the business establishment in order to modify behavior of the shopper as well as to adjust resources based upon inferred results of the modified behavior.

Abstract: The claimed subject matter relates to an architecture that can aggregate user information in order to provide shopping route optimization. The architecture can collect data from users or business establishments, and can further make inferences about a user based upon histories, behavior, query responses, as well as from other suitable data sources. By providing the shopping route optimization, the architecture can gain access to rich sets of information, which can in turn improve the optimizations, potentially creating a virtuous cycle.

Abstract: The claimed subject matter relates to an architecture that can filter or organize content such as advertisements that are either received by or transmitted to a mobile device. The filtering or organizing can be based upon local attributes associated with the mobile device (e.g., location, velocity, time, a profile), as well as based upon attributes associated with the advertiser (e.g., inventory, customer traffic). In addition, the architecture can provide for selection and/or display of advertisements based upon a bidding model, wherein advertisers can bid for mobile devices that exhibit certain characteristics.

Abstract: Useful information is acquired from a community of individuals by way of a game that rewards participants with social information about other participants. Points can be awarded to participants simply for participation and/or as a function of game performance. Such points can subsequently be exchanged to reveal information about game partners or other community members. Among other things, such a reward system can motivate individuals to perform tasks that might not otherwise be compelling and/or enjoyable.

Abstract: Match criteria are provided to specify when advertisements will be shown, for instance in a search environment. Input such as search queries can be represented in a simplified form such as an implicit and/or explicit wildcard expression. Advertisers or other entities can bid on terms such that advertisements or similar content are presented when the terms match an expansion of a simplified input. Matching ads can subsequently be displayed alone or in combination with query expansion suggestions and/or query results.

Abstract: On-line and/or off-line advertisement interactions are tracked for individual users. This information can then be utilized to adjust display parameters for an advertisement. Tracking can be accomplished via a client-side tracking mechanism and/or a server side tracking mechanism. The advertisement interactions allow advertisers to adjust their advertising campaigns to better target their advertisements. The tracked interactions can include, but are not limited to selections (clicking, etc.) and/or conversions (purchases) and the like. Some instances include a display component that can employ the user-specific interaction information to automatically adjust, for example, location, frequency, and/or to whom an advertisement is displayed. The interaction information can also be utilized for revenue generation by charging advertisers for the information and/or for adjusting their advertising campaigns and the like. Instances can be utilized with on-line and/or off-line advertising media.

Abstract: For a multi-party advertising exchange including advertising and publishing entities from disparate advertising networks, flexible advertising transaction accounting methods are provided for circumstances where a relatively small number of trusted participants agree to reduce onerous reporting requirements conducted at a per transaction level. Trusted participants optionally report aggregate data for transactions including aggregate fraud data measurements to determine aggregate apportioning of cost and payments associated with advertising transactions. Aggregate reporting, subject to safeguards, enables a reduction in the overhead associated with per transaction accounting, and other participants need not duplicate measurements of trusted participants who are positioned best to collect the measurements, enabling a cooperative effort to the benefit of all of the trusted participants.

Abstract: For a multi-party advertising exchange including advertising and publishing entities, each publishing entity can expose user attribute space(s) for its publishing inventory to the exchange, which are normalized to a common vocabulary within the exchange. Similarly, each advertising entity can specify one or more preferences for user attributes as requirements or definitions for advertising transactions in the exchange which are also normalized to the common vocabulary. The common vocabulary enables the comparison of a first set of user attributes to a second set of user attributes within the exchange. Supplemental user attribute data may also be received from audience data brokers, and the performance of advertising as a function of sets and subsets of user attributes over time may be recorded so that optimal display strategies can be determined.

Abstract: For a multi-party advertising exchange, including publishing entities and advertising entities from disparate advertising networks, which facilitates transactions for publishing inventory, a value add broker is provided to aggregate information from third parties having valuable information for input to the exchange or to perform services that are valuable to transactions in the exchange. The valuable information or services further facilitate the transactions for the publishing inventory automatically generating a benefit for the third parties providing the valuable information or services commensurate with the value added to the transactions.

Abstract: For a multi-party advertising exchange including advertising and publishing entities, automatic value sharing is provided for distributed users of the advertising exchange that provide valuable information to the exchange. Users provide information that has quantifiable value to the advertising exchange and/or its participants. In exchange for the information, predicated on any function or cost model for quantifying the value of the information, a reward or advantage, such as revenue, is given to the user by the advertising exchange and/or participants of the advertising exchange in order to incentivize users' valuable contributions. As a result, the advertising exchange becomes a more efficient marketplace, increasing predictability and the participant(s) benefit in correspondence with the value of any information received by those participant(s). Various refinements are provided and disclosed according to a host of optional embodiments.

Abstract: An optimization tool is provided for individual participants who participate in multiple online advertising environments wherein the tool interfaces with the multiple environments in an optimal manner on behalf of the individual participants. A participant using the tool can specify goals and/or constraints for participating in one or more of the networks, and then the tool automatically optimizes advertising expenditure for advertising transactions across the different networks. The tool also tracks the performance of the participant across the different networks and dynamically tunes the participant's advertising expenditure based on such performance as well as the changing conditions of the marketplace.

Abstract: For a multi-party advertising exchange including advertising and publishing entities, each participant can specify one or more utility functions that are invertible with respect to a common measure, such as revenue. In one non-limiting embodiment, each utility function is invertible with respect to expected revenue per standard advertising unit, e.g., expected cost per impression. The disparate utility functions of multiple participants are also normalized within the advertising exchange by converting the utility functions to the common measure enabling the comparison or translation of a first set of utility functions to a second set of utility functions in quantifiable terms. Various system refinements are provided and disclosed according to a host of optional embodiments.

Abstract: For a multi-party advertising exchange including advertising and publishing entities, each participant can specify one or more utility functions that are invertible with respect to a common measure, such as revenue. In one non-limiting embodiment, each utility function is invertible with respect to expected revenue per standard advertising unit, e.g., expected cost per impression. The disparate utility functions of multiple participants are also normalized within the advertising exchange by converting the utility functions to the common measure enabling the comparison or translation of a first set of utility functions to a second set of utility functions in quantifiable terms. Various system refinements are provided and disclosed according to a host of optional embodiments.

Abstract: For a multi-party advertising exchange including advertising entities and publishing entities from different advertising networks, automatic apportioning of advertising transactions across inventory from different advertising channels is provided. Optimal combinations or advertising bundles of different channels are generated for the participant based on an analysis of inventory across different advertising channels for a given set of participation goals/constraints. A small portion of a participant's overall advertising expenditure can be held back for exploratory purposes to determine better combinations of advertising channels based on actual performance over time.

Abstract: For a multi-party online advertising exchange including advertising and publishing entities and one or more third party participants, the disclosed systems and methods enable third party participation in arbitrage opportunities in online advertising transactions. A plurality of underlying transaction details are abstracted and provided to the third party participants without loss of generalization and while preserving relationships in the transaction data, to enable a third party share risk in advertising transactions. Various system refinements are provided and disclosed according to a host of optional embodiments.

Abstract: For a multi-party advertising exchange including advertising and publishing entities from different advertising networks, the invention provides architectures for an online advertising marketplace that range from lightweight to heavyweight implementations. A lightweight client side implementation of an interface includes centralized processing and storage of federated advertising marketplace data by centralized servers or services. A heavyweight client side implementation of an interface for advertising entities includes providing a peer instance of a federated advertising exchange application or set of processes is provided to each advertising entity as an interface for advertising entities where processing and storage are performed locally to each peer instance. Distributed advertising data can be replicated or synchronized with other peer instances.

Abstract: For a multi-party advertising exchange including advertising and publishing entities, each participant can specify one or more display properties as requirements or definitions for advertising transactions in the exchange. The disparate display properties of multiple participants are normalized within the advertising exchange to a common vocabulary by translating the display properties to a common set of representations within the exchange enabling the comparison of a first set of display properties to a second set of display properties. The invention also optionally records the performance of advertising as a function of display properties over time so that optimal display strategies can be determined by participants with access to the performance information. Various system refinements are provided and disclosed according to a host of optional embodiments.

Abstract: For a multi-party advertising exchange including advertising and publishing entities, each participant specifies tax rate(s), such as import tax and export tax, that apply to at least one other entity in the exchange. Since tax rate(s) can be expressed in different transactional terms by different parties, each tax rate is reduced to a common tax rate expression within the exchange for comparison. Intelligent tax rate selection and support can be provided to dynamically set tax rates that achieve utilitarian goals for the individual participants taking into account the tax rates expressed by other participants and their respective advertising goals, and dynamically adjusting tax rates over time in response to condition changes. Various refinements are provided and disclosed according to a host of optional implementations.

Abstract: For a multi-party advertising exchange including advertising and publishing entities from disparate advertising networks, a framework is provided for applying insurance terms to advertising transactions in the exchange, enabling risk sensitive participants to ease their participation in a potentially volatile online advertising marketplace. Participants can use the insurance mechanism of the advertising exchange to reduce variance in expected outcome for transactions in the advertising exchange.