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 or extension to a window manager. In particular, the extension can provide for a window rotation feature that can be exposed as a rotate button. Additionally or alternatively, the rotation feature can be activated based upon a diverse set of conditions, events, and/or commands. Upon activation of the rotation feature, the window manager can rotate a window about an axis to expose a secondary surface that can be populated with alternative content that is distinct from the content of the primary surface of the window. In addition, the architecture provides techniques for identifying both double-sided graphical objects and potentially double-sided objects.

Abstract: The claimed subject matter relates to an architecture that can quantify a value of a consumer transaction to a market ecosystem. The value to the ecosystem of the transaction can be based upon features of the transaction as well as dynamics unique to the ecosystem. In addition, the value can be monetized as well as aggregated in order to produce a net economic value of a set of transactions involving a particular consumer. The architecture can further facilitate a repatriation of all or portions of the net economic value to the consumer, potentially based upon ranking and/or loyalty tiers.

Abstract: The claimed subject matter relates to an architecture that can facilitate verification or feedback in association with consumer transactions. In particular the architecture can image a transaction receipt, translate the image into text-based data, and extract relevant transaction data there from. Such relevant transaction data can be saved to a data store maintained or supervised by the customer and/or transmitted to authorized components that can benefit from data related to transaction histories, verification, and/or feedback.

Abstract: The subject disclosure pertains to systems and methods that facilitate detection of cloaked web pages. Commercial value of search terms and/or queries can be indicative of the likelihood that web pages associated with the keywords or queries are cloaked. Commercial value can be determined based upon popularity of terms and/or advertisement market value as established based upon advertising revenue, fees and the like. Commercial value can be utilized in conjunction with term frequency difference analysis to identify a cloaked page automatically. In addition, commercial values of terms associated with web pages can be used to order or prioritize web pages for further analysis.

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: 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: Data slices of historical time series are leveraged to facilitate in more accurately predicting like data slices of future time series. Different predictive models are employed to detect outliers in different data slices to enhance the accuracy of the predictions. The data slices can be temporal and/or non-temporal attributes of a data set represented by the historical time series. In this manner, for example, a historical time series for a network location can be sliced temporally into one hour time periods as a function of a day, a week, a month, a year, etc. Outliers detected in these data slices can then be mitigated utilizing the predictive time series model by replacing the outlier with the expected value. The mitigated historical time series can then be employed in a predictive model to predict future web traffic for the network location (and advertising revenue values) with a substantial increase in accuracy.

Abstract: A system that incorporates an interactive graphical user interface for visualizing clusters (categories) and segments (summarized clusters) of data. Specifically, the system automatically categorizes incoming case data into clusters, summarizes those clusters into segments, determines similarity measures for the segments, scores the selected segments through the similarity measures, and then forms and visually depicts hierarchical organizations of those selected clusters. The system also automatically and dynamically reduces, as necessary, a depth of the hierarchical organization, through elimination of unnecessary hierarchical levels and inter-nodal links, based on similarity measures of segments or segment groups. Attribute/value data that tends to meaningfully characterize each segment is also scored, rank ordered based on normalized scores, and then graphically displayed.

Abstract: Advertiser monetization information is utilized to determine a search query monetization value that can be employed in web-search ranking to facilitate in ranking search results and/or in email spam filtering to reduce unsolicited emails and the like. Various methods can be employed to filter and/or rank and the like based on the search query monetization value. This can include biasing based on high values and/or low values. The search query monetization value can be determined based on, for example, independent phrases and/or bids. In other instances, personal user advertising interactions can be employed as well to facilitate search result ranking and/or email spam filtering. Employment of search query monetization value techniques can substantially reduce various types of subversive/undesired information.

Abstract: Enhancements to Bayesian prediction models for network location traffic provide increased accuracy in web traffic predictions. The enhancements include implementing user advertising target queries to determine preferred edges of a Bayesian model, employing hierarchical data structures to cleanse training data for a Bayesian model, and/or augmenting existing data with new training data to enhance a previously constructed Bayesian model. Preferred edge enhancements for the Bayesian model utilize target attribute derived preferred edges and/or explicitly specified preferred edges. Training data is cleansed utilizing tag hierarchies that can employ parent-child relationships, ancestor relationships, and/or network location specific parameters. New training data can also be employed to adjust probabilities in a previously constructed Bayesian model. The new training data can be weighted differently than data represented by the previously constructed Bayesian model.

Abstract: Systems and methods are described that facilitate learning a Bayesian network with decision trees via employing a learning algorithm to learn a Bayesian network with complete tables. The learning algorithm can comprise a search algorithm that can reverse edges in the Bayesian network with complete tables in order to refine a directed acyclic graph (DAG) associated therewith. The refined complete-table DAG can then be employed to derive a set of constraints for a learning algorithm employed to grow decision trees within the decision-tree Bayesian network.

Abstract: A service manager manages connection tokens in a network of users. The connection token has a plurality of defined terms and can be representative of a commitment of time for a user in the network. Connection tokens can be used to engage in a real-time communication with another user in exchange for a fee. The service manager manages possession of the connection tokens amongst the users of the network and executes the connection token in accordance with the defined terms. Additionally, the service manager can facilitate real-time communication among users based on the connection tokens.

Abstract: A service manager manages information solicitations in a network of users. An information solicitation is posted that is received from an information consumer. The posted information solicitation is provided to at least a portion of the users of the network for auction. The information solicitation includes a request to engage in a real-time communication with an information provider about a particular subject. Bids are received from a plurality of information providers. The bids are provided to the information consumer for selection. The information consumer is connected with a selected one of the plurality of information providers.

Abstract: A speech application accessible across a network is personalized for a particular user based on preferences for the user. The speech application can be modified based on the preferences.

Abstract: Tasks based on status information are performed based on a voice query across a computer network. Information in the voice query is associated with a particular contact entity and status information is accessed in order to perform the tasks.

Abstract: Random samples without replacement are extracted from a distributed set of items by leveraging techniques for aggregating sampled subsets of the distributed set. This provides a uniform random sample without replacement representative of the distributed set, allowing statistical information to be gleaned from extremely large sets of distributed information. Subset random samples without replacement are extracted from independent subsets of the distributed set of items. The subset random samples are then aggregated to provide a uniform random sample without replacement of a fixed size that is representative of a distributed set of items of unknown size. In one instance, a multivariate hyper-geometric distribution is sampled by breaking up the multivariate hyper-geometric distribution into a set of univariate hyper-geometric distributions.

Abstract: The present invention provides a unique system and method that can employ machine learning techniques to automatically fill one or more fields across a diverse array of web forms. In particular, one or more instrumented tools can collect input or entries of form fields. Machine learning can be used to learn what data corresponds to which fields or types of fields. The input can be sent to a central repository where other databases can be aggregated as well. This input can be provided to a machine learning system to learn how to predict the desired outputs. Alternatively or in addition, learning can be performed in part by observing entries and then adapting the autofill component accordingly. Furthermore, a number of features of database fields as well as constraints can be employed to facilitate assignments of database entries to form values—particularly when the web form has never been seen before by the autofill system.

Abstract: The present invention leverages scalable learning methods to efficiently obtain a Bayesian network for a set of variables of which the total ordering in a domain is known. Certain criteria are employed to generate a Bayesian network which is then evaluated and utilized as a guide to generate another Bayesian network for the set of variables. Successive iterations are performed utilizing a prior Bayesian network as a guide until a stopping criterion is reached, yielding a best-effort Bayesian network for the set of variables.

Abstract: The present invention leverages machine learning techniques to provide automatic generation of conditioning variables for constructing a data perspective for a given target variable. The present invention determines and analyzes the best target variable predictors for a given target variable, employing them to facilitate the conveying of information about the target variable to a user. It automatically discretizes continuous and discrete variables utilized as target variable predictors to establish their granularity. In other instances of the present invention, a complexity and/or utility parameter can be specified to facilitate generation of the data perspective via analyzing a best target variable predictor versus the complexity of the conditioning variable(s) and/or utility. The present invention can also adjust the conditioning variables (i.e.