Abstract: Devices and techniques are generally described for machine learning personalization as a service for speech processing applications. In various examples, a first request for machine learning prediction for a first speech processing skill. First skill data schema data may be received that describes content of the first speech processing skill. A first machine learning model for the first speech processing skill may be determined. A first feature definition describing a first aspect of the content may be determined. A second feature definition describing user profile data may be determined. A prediction request may be received from the first speech processing skill. First feature data may be generated according to the first feature definition and second feature data may be generated according to the second feature definition based at least in part on the prediction request.

Abstract: Techniques for a geofence generation feature are described herein. Geospatial vector data for a geographical area and seed points for delivery locations within the geographical area may be obtained. A plurality of polygons that represent the geographical area may be determined based on an algorithm that uses the seed points and the geospatial vector data. A boundary point for each polygon may be determined based on coordinates for the plurality of polygons where each boundary point corresponds to a single seed point. A geofence of a first size may be generated, for each polygon, based on the coordinates for the polygons, the seed point, and the boundary point. Historical scans of GPS data may be obtained from user devices during historical visits to the geographical area. The geofence may be modified to a second size or a different shape based on the historical scans of the GPS data.

Abstract: In general, embodiments of the present invention provide for ranking data objects using machine learning and scoring to configure a graphical interface. In this regard, a machine learning model is applied to data object attributes to generate data object relevance scores for the candidate data objects. Additionally, a respective personalization score for the candidate data objects is generated based at least in part on a compounded ratio and a geometric mean of the compounded ratio. The data object relevance scores for the candidate data objects are modified based at least in part on the respective personalization score for the candidate data objects to generate modified object relevance scores for the candidate data objects. The candidate data objects are then ranked based at least in part on the modified object relevance scores to generate a ranked data object set and to facilitate configuration of a graphical interface.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for dynamically augmenting relevance rankings using data from external ratings sources.

Abstract: Techniques for training a machine learning model to determine a predicted time distribution related to electronic communications are discussed herein. The machine learning model is trained based at least in part on time to open data indicative of respective time to open terms that begin at respective transmission times for electronic communications and end at respective electronic communication access event times. Additionally, based at least in part on the predicted time distribution determined by the machine learning model, respective access scores for an electronic communication being accessed via the user device at the respective times are determined to provide a new electronic communication for rendering via an electronic interface of a user device.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for dynamically augmenting relevance rankings using data from external ratings sources.

Abstract: Techniques for integrating freshness and relevance within a programmatic relevance service are discussed herein. Some embodiments may include a relevance service system, including one or more batch processors and one or more online processors. The one or more batch processors may be configured to track message recipient behavior from electronic clickstream data, and generate models of functions that predict access probability for individual users. The one or more online processors may use the access probability calculated in batch to facilitate on demand deal ranking adjustments that account for freshness as informed by the predicted access probability for communications sent to the user.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

Abstract: Systems, methods and techniques disclosed herein provide dynamic time-based adjustment of predictive modeling data.

Abstract: An apparatus, method, and computer program product are provided to filter and modify option data objects and weighted values associated with option data objects through the application of specific rule sets based on the relative density of option data objects within a particularized area. In some example implementations, option data objects and related parameters are parsed to identify locations associated with the option data object and a weighted value, such as a weighted value generated by a predictive model. Based at least in part on the location associated with the option data object, a determined location of a user of a mobile device, and location-specific distance criteria, the weighted value associated with the option data object may be modified to reflect distance-related option election probabilities.

Abstract: Embodiments are provided that improve persona tracking and use to improve the accuracy of determinations and actions that rely on such persona(s). Some example embodiments track user information associated with a profile. Example embodiments further generate personas associated with the profile based on the user information. Example embodiments further receive time data and/or location data from a user device. Example embodiments further determine a selected persona based on the time data and/or the location data. Example embodiments further determine a preference dimension value based on the selected persona. Example embodiments further identify promotion data representing a plurality of promotions. Example embodiments further, for each promotion, generate a first dimension score corresponding to the preference dimension value based on the selected persona. Example embodiments further determine a ranking for the promotions based on the first dimension score for each promotion.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

Abstract: A method implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable medium being operable to associate each of a plurality of tenants with a respective virtual portal and individually meter virtual portal usage at each respective virtual portal. Additionally, the computer executable code is operable to determine a fee amount for the each of the plurality of tenants based on the individually metered virtual portal usage.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

Abstract: An apparatus, method, and computer program product are provided to filter and modify option data objects and weighted values associated with option data objects through the application of specific rule sets based on the relative density of option data objects within a particularized area. In some example implementations, option data objects and related parameters are parsed to identify locations associated with the option data object and a weighted value, such as a weighted value generated by a predictive model. Based at least in part on the location associated with the option data object, a determined location of a user of a mobile device, and location-specific distance criteria, the weighted value associated with the option data object may be modified to reflect distance-related option election probabilities.

Abstract: Systems and related methods of providing promotional offers to consumers are discussed herein. Some embodiments may provide for an apparatus including circuitry configured to provide promotional offers to consumers based on dimensions representing criteria by which promotions may be deemed relevant to a consumer. Some examples of dimensions may include location, time, environment, price, and/or consumer preference. Based on receiving signals from the consumer device, among other sources, indicating associated times, locations, and other characteristics of consumer activity, the apparatus may recognize patterns or trends in consumer behavior, and use such information to predict or influence future consumer behavior.

Abstract: Embodiments of the present invention address deficiencies of the art in respect to wiring components in a component based application and provide a method, system and computer program product for heuristically assembling components in a component based application. In one embodiment, a data processing system configured to assemble component based applications can include a component aggregation application including an application builder configured to assemble components into a component based application. The system further can include a property broker coupled to the component aggregation application and configured to apply a wiring scheme to selected components in a component based application. Finally, a collaborative heuristic integration matching engine (CHIME) can be coupled to the property broker and a data store of behaviorally derived data, the CHIME including program enabled to suggest components for assembly in a component based application based upon behaviorally derived data in the data store.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for a universal relevance service framework for ranking and personalizing items.