Abstract: A sample ratio mismatch (SRM) analyzer receives data from an online controlled experiment (OCE) and provides information to help determine a root cause of an SRM. The SRM analyzer may identify one or more segments in the data that include an SRM and may determine whether a triggered scorecard of the OCE includes an SRM. The data may include one or more scorecards. The SRM analyzer may determine whether each scorecard has an SRM. The SRM analyzer may test a difference in proportion of users assigned to treatment between a last scorecard without an SRM and a first scorecard with an SRM. If the difference in proportion is statistically meaningful, the SRM analyzer may determine that the SRM arose after the last scorecard. If the difference in proportions is not statistically meaningful, the SRM analyzer may determine that the SRM existed from a beginning of the OCE.

Abstract: Social network postings, including text, images or other media, may provide valuable information regarding a user of the social network with which the postings may be associated. With the authorization of the user, and upon authentication by the social network, an online marketplace may access the social network postings and extract data therefrom, and market one or more recommended items to the user based on the extracted data, which may include color pallets or texture pallets derived from photographs included in the postings.

Abstract: An exemplary system, method, and computer-accessible medium for providing a financial account recommendation to person(s) can include receiving a transaction history for the person(s) associated with a first financial account, determining first rewards information based on the transaction history, accessing database(s) containing rewards rates for a plurality of second financial accounts, determining second rewards information for a particular second financial account of the plurality of second financial accounts based on the transaction history, and providing the financial account recommendation to the person(s) to one of (i) keep the first financial account or (ii) switch to the second financial account based on a comparison of the first rewards information to the second rewards information.

Abstract: A cognitive learning method comprising: monitoring a user interaction of an anonymous user; generating user interaction data based upon the user interaction; receiving data from a plurality of data sources; processing the user interaction data and the data from the plurality of data sources to perform a cognitive learning operation, the processing being performed via a cognitive inference and learning system, the cognitive learning operation comprising analyzing the user interaction data, the cognitive learning operation generating a cognitive learning result based upon the user interaction data; and, associating an anonymous cognitive profile with the anonymous user based the cognitive learning result.

Abstract: A method for identifying, contracting, evaluating, bounding, and filtering out uncertainty in survey data is provided. The method includes: receiving survey responses with respect to a customer survey; constructing a simulated numerical model that replicates the structure of the original survey by using responses that are generated randomly from distribution of responses with constraint variability that specifically account for the uncertainty that arises from the subjective nature of sampling response from an ordinal range of possible options; matching between the original survey and the numerical model using a machine learning algorithm; and evaluating and filtering out the uncertainty of the original survey. In addition, a method is offered to constrain and contract the uncertainty by assigning survey responses to corresponding evenly distributed bins and by calibrating the survey responses by attaching a short textual description to each of the ordinal values in the original survey.

Abstract: Example methods, apparatus, and articles of manufacture for media metering are disclosed. An example apparatus disclosed herein includes at least one memory, instructions in the apparatus, and at least one processor installed in a media presentation device to execute the instructions to at least: cause a video decoder to generate video display rasterizing information, present the video display rasterizing information via an output device of the media presentation device, and in response to monitoring being enabled, generate metering information corresponding to media presented in association with the video display rasterizing information presented via the output device.

Abstract: A device may receive customer data associated with customers of items, and may identify customer characteristics based on the customer data. The device may process the customer characteristics, with a first model, to group the customers into groups of customers, and may process item data and data identifying the groups of customers, with a second model, to determine associations between the item data and the groups of customers. The device may receive, from a user device associated with a particular customer, particular customer data, and may identify particular customer characteristics based on the particular customer data. The device may assign the particular customer to a particular group, of the groups of customers, based on the particular customer characteristics, and may generate an item recommendation, for the particular customer, based on the item data associated with the particular group. The device may provide the item recommendation to the user device.

Abstract: A smart circuit breaker may provide a smart-circuit-breaker power monitoring signal that includes information about power consumption of devices connected to the smart circuit breaker. The smart-circuit-breaker power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart circuit breaker, (ii) identify devices receiving power from the smart circuit breaker, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: A system and method in accordance with example embodiments may include providing functionality triggers to a consumer's mobile device in response to using a payment card in order to make a purchase. Functionality triggers may include account functionality, rewards functionality, social networking functionality, and offer or advertisement functionality to be performed on a consumer's mobile device.

Abstract: A computer-implemented method for providing presentable transaction data of a product to a user may include obtaining preliminary transaction data of one or more purchasers other than the user; generating itemized transaction data based on the preliminary transaction data; obtaining one or more translation codes from one or more transaction entities; generating standardized transaction data based on the itemized transaction data and the one or more translation codes; retrieving identification data from the standardized transaction data; generating anonymized transaction data based on the standardized transaction data by withholding the identification data; generating presentable transaction data based on the anonymized transaction data; and transmitting, to a device associated with the user, the presentable transaction data.

Abstract: Methods and systems for starting a node without a default password are provided. Exemplary methods include: creating a node responsive to indicia received from a user; checking for an existing keystore in the node; when no existing keystore is in the node: generating a seed password for a predefined user of the node; non-persistently providing the seed password to the user; creating an encrypted keystore in the node; and storing the seed password in the encrypted keystore; and allowing access to the node using the built-in user and seed password.

Abstract: A device may be configured to monitor operations of at least one application installed on the device. The device may include a processor and a non-transitory memory. When executed by the processor, an application stored in the memory may cause the processor to perform a plurality of operations. A beacon may be embedded in the application. When the application is executed by the processor, the beacon may cause the processor to establish a direct connection with a remote system comprising a storage database, gather data indicative of at least one of the plurality of operations as specified by at least one beacon microservice, and send the data through the direct connection to store the data in the storage database.

Abstract: An example apparatus disclosed herein includes a data input interface to access different sets of initial adjustment factors, the initial adjustment factors generated to correct at least one of misattribution or non-coverage of media impressions logged by a database proprietor, a grouping controller to identify a first set of the initial adjustment factors as a set of donor adjustment factors based on (a) first audience members associated with the set of donor adjustment factors satisfying a first threshold and (b) first impressions associated with the first audience members satisfying a second threshold, and identify a second set of the initial adjustment factors as a set of recipient adjustment factors, and an imputation factor generator to generate imputation factors to correct ones of the recipient adjustment factors based on ones of the donor adjustment factors.

Abstract: An equipment introduction effect analyzer as an information processing apparatus includes: an equipment-related information storage unit that holds equipment data including information on equipment and information on a function and performance included in equipment, and equipment buyer data including information on an effect obtained when an equipment buyer introduces equipment, information on a use environment of the equipment, and information on the purchased equipment; and an evaluation engine unit that generates information on an effect to be provided to a potential equipment buyer based on the information on the effect and the information on the use environment of equipment that are included in the equipment buyer data, and on the basis of information on an environment in which the potential equipment buyer uses the equipment, the equipment buyer data being acquired from the equipment buyer already purchased equipment with a function and performance desired by the potential equipment buyer.

Abstract: Disclosed are various approaches for dynamically creating content to present to a user based on an identified intent, or other context, associated with a message (e.g., email). A message that is received from a message server can be analyzed to identify the message content within the message prior to distributing to the recipient client device. Trained intent identification models can be applied to the identified message content to determine an intent, or other type of context, associated with the message. Upon identifying the intent, the message header can be modified to include the intent prior to forwarding the message to the recipient client device. The client device can then display a user interface including the message and a user interface element corresponding to a third-party service. The user interface element can be dynamically generated to include an action component that upon selection, triggers an action associated with the intent.

Abstract: A system and method for dynamically obtaining and evaluating information to optimize the generation of vehicle suggestions for a customer. A profile based on an initial set of information received from a user is created. Metrics are generated based on the profile information. Upon receiving a vehicle request, the profile and the request are analyzed in view of available vehicles. A customer's response to the vehicle suggestion list, as well as events triggered by a perceived need for additional information result in the dynamic adjustment of the profile and thus, the generated metrics.

Abstract: Systems, methods, and apparatus are provided for integrating access to third-party data using DNA computing. Requests for third-party data may be received from a plurality of applications. The request structure may be tagged with an NFT, linking the request to the originating application. DNA strands may be synthesized from the request structures and clustered based on the encoded attributes. A DNA cluster may be converted to digital data to generate an integrated request structure. Machine learning models may generate an extraction schedule using update information for each third-party vendor. A bot array may apply license credentials to access the vendors and execute an integrated request. An integrated response structure generated from extracted subscription data may be mapped back to the DNA strands. The DNA strands may be decoded to identify the original requests and responses may be transmitted to the originating applications using the NFT linkage associated with the requests.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining historical data of demand response programs and demand response agreements respective to each of the users regarding a subject energy. Training dataset for a DR user pooling model includes attributes of the demand response data collected that are relevant to responsivities of the demand response programs. The DR user pooling model is trained by the training dataset by machine learning. A DR user pool is identified amongst users of the demand response program by the DR user pooling model. Users in the DR user pool respond to demands as a group and the DR user pool is adjusted to improve responsivities of the demand response programs.

Abstract: A system and method for providing real estate spatial analysis through a user interface which allows the user to visualize the analysis through maps. A businesses are identified within each of a number of incremental areas of an overall map area. Corresponding land use types are identified for the incremental areas. A predominant land use type is identified for each incremental area. A land use map is generated with colors the respective incremental area using a predetermined color assigned to the predominant land use type for the respective incremental area.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network that is configured to receive a network input and to generate a network output for the network input. The neural network comprises a plurality of layers arranged in a sequence, including a plurality of capsule layers. Each particular capsule in a particular capsule layer is configured to receive respective inputs including: (i) outputs generated by capsules of a previous capsule layer that is before the particular capsule layer in the sequence, and (ii) final routing factors between capsules of the previous capsule layer and the particular capsule, wherein the final routing factors are generated by a routing subsystem. Each particular capsule in the particular capsule layer is configured to determine a particular capsule output based on the received inputs, wherein the particular capsule output is of dimension greater than one.

Abstract: Novel tools and techniques for an IoT shell are provided. A system includes an internet of things (IoT) device, a database, and a license manager. The database may include one or more sets of authorized licenses, each set of authorized licenses associated with a respective vendor software. The license manager may be in communication with the IoT device and the database, and further include a processor and a non-transitory computer readable medium comprising instructions executable by the processor. The license manager may be configured to receive a request to reserve a license for a first vendor software, determine an availability of the license associated with the first vendor software, register a unique identifier of the IoT device in association with the license, and grant the license to the IoT device.

Abstract: A computing system for encouraging the performance of a task comprises association data, a proxy module, a display module, and a reward module. The association data associates tags with stimuli related to performing tasks. The proxy module is configured to receive encoded data, to identify tags in the encoded data that have associated stimuli in the association data, and to generate modified encoded data that includes data representative of at least one of the stimuli. The display module is configured to receive the modified encoded data, to display information based at least in part on the modified encoded data, and to provide at least one mechanism for a user to perform a task related to at least one of the stimuli. The reward module is configured to reward a user for performing tasks related to the stimuli.

Abstract: Systems and methods are provided for receiving a request for forecasting data to use for new product introduction, the request comprising an indication of a plurality of existing products and accessing data for a plurality of existing curves corresponding to the plurality of existing products. The systems and methods further provide for, based on determining that at least a subset of curves of the plurality of curves comprises a plurality of values, analyzing each value of the plurality of values for each curve of the subset of curves to determine a maximum number of values among all of the curves of the subset of curves, generating a text file comprising a maximum number of value columns corresponding to the maximum number of values, and populating the text file with the data for the plurality of existing curves, including the plurality of values for each curve of the subset of curves.

Abstract: Systems and methods are disclosed for determining segments of online users from a correlated dataset. One method includes receiving, over a network, a plurality of datasets including user-related data of a plurality of users, each dataset being transmitted from a data owner; correlating, by at least one processor, the plurality of datasets into a correlated dataset; receiving a segmentation request for determining a plurality of users that qualify for a segment, the segmentation request including a set of segment rules to apply to the correlated dataset; determining, by accessing the correlated dataset, whether each user of the plurality of users qualifies for the segment based on the segment rule; and storing an indication of the segment in the correlated dataset for each user determined to qualify for the segment.

Abstract: Techniques for enhancing usability and electronic resource efficiency using job relevance are disclosed herein. In some embodiments, a list of a predetermined number of top job openings for a member of the social networking system is generated. The list is communicated to a device of the user for presentation in a user interface on the device. The user interface allows the member to browse through and provide an indication of a lack of relevancy of each of the list of the predetermined number of top job openings to the member and an indication of a reason for the lack of relevancy. Based on the user providing the indication of the lack of relevancy and the reason, a modified relevancy assessment of each of the plurality of job openings is generated. The list of the predetermined number of top job openings for the member is regenerated and communicated to the device.

Abstract: A method for managing and providing compensation between devices in order to encourage positive behavior is disclosed. The system is operable to receive a request for providing compensation to a user account and is further operable to fulfil the request, track the compensation transfer, and provide historical data of the transfer based on geographic location. The geographic locations preferably include multiple tiers of permissions that are managed by multiple governing entities.

Abstract: Technology is disclosed for facilitating and processing cross-merchant promotions. In examples, the disclosed technology comprises processing transaction data for a first merchant and a second merchant that includes identifiers for merchant, customer, location, and item; generating a recommendation for the merchants to participate in a cross-merchant promotion based on a determination that they are complementary; facilitating a notification of the promotion to customers; receiving transaction data for another transaction of the first merchant; applying the promotion to the transaction based on a customer transaction history of the customer; processing payment for the transaction; apportioning the payment to the first and second merchant according to an agreement between them; and presenting a notification of application of the promotion on a merchant device.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: Introduced here are communication optimization platforms configured to improve comprehension, persuasion, or clarity of communications. Initially, a communication optimization platform can acquire input sample(s) that are associated with a source audience. The communication optimization platform can then create a linguistic profile for the source audience by examining the content of the input sample(s). Additionally or alternatively, the communication optimization platform may produce a psychographic profile that specifies various characteristics of the source audience, such as personality, opinions, attitudes, interests, etc. The communication optimization platform can then generate, based on the linguistic profile and/or the psychographic profile, affinity language for communicating with a target audience. By incorporating the affinity language into communications, the communication optimization platform can increase appeal to the target audience.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: A system and a method provide a lead verification service. A lead generator contacts a verification server when a visitor lands on a hosting site of the lead generator to enter lead information into a form. The verification server issues a reference key (token) to the lead generator and collects information about the visitor and the hosting site of the lead generator, using the reference key to identify the collected information. When the visitor submits the form, the lead generator sends the form data, which includes the entered lead information and the reference key received from the verification server, to at least one interested party. When the verification server receives a request for the collected information from the interested party, the collected information is retrieved based on the reference key included in the request and sent to the requesting interested party.

Abstract: Systems and methods for secure sharing of sensitive information in a computing environment. The methods comprise, by a first entity of a first computing environment receiving sensitive information of the first computing environment, receiving a request to share the sensitive information from a second entity of the first computing environment, and determining whether the second entity is a trusted entity included in a list of trusted entities held by a configuration service associated with a second computing environment. If the second entity is not a trusted entity, determining whether the second entity can establish trust by validating a subscription of the second entity with a directory service, and validating a digital certificate corresponding to the second entity with a certificate authority. If the second entity can establish trust or is a trusted entity, sharing the sensitive information with the second entity so as to enable operation of the second entity.

Abstract: Methods and system for planning and optimizing the recovery of critical infrastructure resources, where the method includes determining, from execution of a computer readable code, impact of at least one predetermined environmental condition on a number of critical infrastructure resources subjected to said predetermined environmental conditions and on other critical infrastructure resources dependent on said number of critical infrastructure resources, each of the number of critical infrastructure resources having rules for impact of predetermined environmental conditions and for recovery time, obtaining, from execution of the computer readable code, deployment information for predetermined Recovery Assets, each one of the predetermined Recovery Assets being staged, before deployment, at a predetermined staging location, and obtaining, from execution of the computer readable code, resulting consequences from deployment of the predetermined Recovery Assets.

Abstract: Provided herein is a holistic fraud cocoon that protects a user from incoming or outgoing fraud and phishing communications by capturing, analyzing and either altering, discarding or presenting communications to the user. For example, the holistic fraud cocoon captures all incoming sources (mail, in-person visits, phone, TV, radio, newspapers and internet) and the actions performed by the user, triggered by those sources. Certain actions are held in a queue to be reviewed, validated and acted upon by a third party before the actions are executed.

Abstract: Methods, apparatus, systems and articles of manufacture to determine headphone adjustment for portable people meter listening to encoded audio streams are disclosed.

Abstract: A method according to an aspect of the present disclosure includes combining pieces of first feature data and pieces of second feature data. Each of the pieces of first feature data is associated with first identification information related to a corresponding one or more of first constituents included in a first group and indicates a feature of the corresponding one or more of the first constituents. Each of the pieces of the second feature data corresponds to one of clusters in the second group. The second feature data includes statistic data associated with second identification information related to two or more of the second constituents included in a corresponding cluster. The statistic data has a statistic indicating a feature of two or more of the second constituents included in the corresponding cluster. The combining is performed based on the first identification information and the second identification information.

Abstract: Mapping anonymous Internet entities to known accounts. In an embodiment, events, representing online activity and comprising IP addresses, are received from a plurality of sources. Subsets of the events are aggregated into mappings that associate the IP address, shared by the subset, with an account. Each mapping is associated with statistics regarding the events. A confidence value is calculated for each mapping based on the statistics, and a final subset of the mappings is selected based on the confidence values. Subsequently, when a request with an IP address is received, the final subset of mappings is searched for the requested IP address, and an indication of the account associated with the requested IP address is returned in response to the request.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: The present invention discloses a method of detecting an abusing act in an online service, the method including: a use act information collecting operation in which an apparatus for detecting an abusing act collects use act information including the kinds and an order of one or more use acts performed by a user; an image configuring operation in which the kinds of the one or more use acts performed by the user are arranged in a time order and an image is configured by setting the kinds of predetermined use acts to a first axis and setting the order of the use acts to a second axis; and an abusing act detecting operation in which whether the use act of the user is an abusing act is detected by using the image.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Abstract: Systems and method of generating video summaries are presented herein. Information defining a video may be obtained. The video may include a set of frame images. Parameter values for parameters of individual frame images of the video may be determined. Interest weights for the frame images may be determined. An interest curve for the video that characterizes the video by interest weights as a function of progress through the set of frame images may be generated. One or more curve attributes of the interest curve may be identified and one or more interest curve values of the interest curve that correspond to individual curve attributes may be determined. Interest curve values of the interest curve may be compared to threshold curve values. A subset of frame images of the video to include within a video summary of the video may be identified based on the comparison.

Abstract: Methods and apparatus to partition data are disclosed. An example apparatus to partition panelist data includes an indicator matrix generator to determine an indicator matrix including panelist vectors for panelists based on panelist data associated with the panelists, a first one of the panelist vectors for a first one of the panelists to indicate whether the first one of the panelists: has a first characteristic, meets a first criterion based on the first characteristic and a second characteristic, has a third characteristic, and meets a second criterion based on the third characteristic and a fourth characteristic. The example apparatus further includes a matrix reducer to reduce the indicator matrix to a set of unique panelist vectors that represent partitions of the panelist data, the partitions of the panelist data to utilize less storage capacity than the panelist data.

Abstract: A system and method is provided for generating new product offerings for display in which products are decoupled into components and the components are weighted based on user-specific preferences and market trends. The weighted components are then recompiled into new product offerings based on a probabilistic selection. Each component may be associated with related or otherwise applicable components and these associated components may also be incorporated into a new product offering for display during the probabilistic selection process. The selection and display process may also be tailored to specific users by adjusting weights based on preferences of those specific users.

Abstract: At an artificial intelligence-based service, an indication of a similarity group of items of a data stream is obtained. A subset of the stream items is to be included in an ordered collection and presented via an interface which allows one or more types of interactions. Using a first data set which includes interaction records of items in the similarity group, one or more machine learning models are trained to predict a relevance metric associated with a particular type of interaction. A predicted value of the relevance metric is obtained from a trained version of a model and stored.

Abstract: A system and a method disclosed herein provides search and recommendation mechanisms for selecting attorneys. In an embodiment, a processor identifies a claim litigated by a candidate attorney. The processor uses historical claim data and a claim score for an attorney who opposed the candidate attorney when litigating the claim to determine a claim score for the candidate attorney. The processor then uses the candidate attorney claim score to recalculate the opposing attorney claim score, and checks to see whether the claim scores have converged. If the scores have not converged, the processor iteratively recalculates the claim scores of the candidate attorney and the opposing attorney until the scores converge. Finally, the candidate attorney claim score is used to determine an overall score for the candidate attorney which can be compared against the scores of other attorneys and used for attorney search and recommendation.

Abstract: An abstraction system for generating a standard customer profile in a data processing system has a processing device and a memory. The abstraction system may receive customer data from a computing device over a network and perform unsupervised learning on the customer data to produce a plurality of clusters of customers with a first feature in common. The abstraction system performs unsupervised learning on the plurality of clusters of customers to produce a plurality of sub-clusters of customers with a second feature in common, and repeats the unsupervised learning on the plurality of sub-clusters produced to produce further sub-clusters with a plurality of features in common. The abstraction system determines that a sub-cluster represents a standard customer and stores a plurality of standard customer profiles based on the determined standard customers. The abstraction system provides the standard customer profiles to a cognitive system for generating synthetic transaction data.