Abstract: A system is provided for estimating quantile values for fraud assessments. The system includes a processor and a computer readable medium operably coupled thereto, to perform operations which include capturing one or more first data values for a quantile value profile associated with an entity, wherein the quantile value profile includes one of real values or a first plurality of quantile marker values calculated from the real values, accessing the quantile value profile for the entity, determining a first number of the one or more first data values, and based on the first number of the one or more first data values and the one of the real values or the first plurality of quantile marker values in the quantile value profile, performing one of a first merge operation, a second merge operation, or a third merge operation.

Abstract: Embodiments provide a computer-executable method, computer system and non-transitory computer-readable medium for programmatically analyzing a consumer review. The method includes programmatically accessing, via a network device, one or more consumer reviews for a commercial entity or a commercial object. The method also includes executing a consumer review processing engine to programmatically identify an attribute descriptor in the one or more consumer reviews, and executing the consumer review processing engine to programmatically generate a sentiment score associated with the one or more consumer reviews. The method further includes storing, on a non-transitory computer-readable storage device, the attribute descriptor and the sentiment score in association with the commercial entity or the commercial object.

Abstract: A data processing system for machine-learning driven data analysis and reminders implements obtaining an electronic copy of demographic information and an electronic copy of insurance and benefits information associated with a user; providing the demographic information and the insurance and benefits information to a first machine learning model; analyzing the demographic information and the insurance and benefits information with the first machine learning model to output a first benefits utilization prediction that the one or more benefits are available to the user; providing the first benefits utilization prediction as an input to a recommendation engine; generating, using the recommendation engine, a benefits usage summary recommendation report that presents the information regarding the one or more benefits available to the user based on the first benefits utilization prediction; and causing a user interface of a display of a computing device to present the benefits usage summary recommendation report.

Abstract: Technologies pertaining to assigning patients to patient populations and graphically indicating that the patients have been assigned to the patient populations are described herein. A graphical user interface includes interactive elements that are configured to indicate to a healthcare worker that a patient has been assigned to a population, and further to depict proposed actions based upon the patient being assigned to the population.

Abstract: Systems, methods, and computer-readable media are provided for hybrid guidance of a communication session. In one aspect, a system includes one or more processors configured to execute computer-readable instructions to receive an inquiry from a user terminal; stream the inquiry to one or more support terminals configured to provide live support for the inquiry; determine if an automated response to the inquiry is available; and provide one of the automated response or a live response to the inquiry based on whether the automated response to the inquiry is available or not.

Abstract: Disclosed are methods, systems, and devices for identifying anomalous and/or problematic payments based on past payment patterns of a user, past experiences with the user, and the user's circumstances, and implementing intervention mechanisms for proactively resolving account issues before downstream impacts, such as collections calls, inbound calls, and complaints. Anomalous payments may be detected using clustering and prediction. Interventions may include phone calls, emails, notifications, etc. An alert or notification may be sent to the user's mobile application, and various selectable response options suited to the situation may be presented to the user.

Abstract: Techniques for automatically collecting data and updating social media profiles based on sensor data are discussed herein. A system can comprise an activity identification component that based on sensor data received by the activity identification component, identifies an activity associated with an entity of a mobile device, resulting in an identified activity. Additionally, the system can comprise an updating component that based on the identified activity, updates a social media profile associated with the activity with activity data related to the identified activity.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for assisting an agent in providing support to a customer. The methods, systems, and apparatus include actions of obtaining interaction information regarding an interaction between a customer and an agent, identifying the customer from the interaction information, aggregating the information regarding the customer from multiple sources, determining an intent of the customer from the interaction information and the aggregated information, determining a sentiment of a customer from the interaction information and the aggregated information, determining a particular action to indicate to the agent based on the aggregated information, the intent, and the sentiment, and generating an interface to provide the agent based at least on the particular action.

Abstract: Techniques for determining value of a home by applying one or more neural network models to images of spaces in the home. The techniques include: obtaining at least one image of a first space inside or outside of a home; determining a type of the first space by processing the at least one image of the first space with a first neural network model; identifying at least one feature in the first space by processing the at least one image with a second neural network model different from the first neural network model and trained using images of spaces of a same type as the first space; and determining a value of the home at least in part by using the at least one feature as input to a machine learning model different from the first neural network model and the second neural network model.

Abstract: Machine learning-based approaches are used to detect trends of behavior and anomalous events from customer support messages between customers and customer support agents or other appropriate resources in an electronic environment. For example, for a plurality of time periods, a prediction model can be trained. The prediction models can be trained on messages that correspond to each prediction models' period of time. The prediction models can process messages to determine a score (e.g., a representative confidence score) for the time period a prediction model is associated with. For a selected time period, a model (e.g., a trend detection model) can be applied to the scores for time periods before the selected time period to determine whether the score for the selected time period is associated with an anomalous event. Thereafter, an alert can be presented with, for example, the messages that triggered the alert, among other such information.

Abstract: A computer-implemented method, computer program product, and computing system for receiving a contribution for a social platform from a client; funding the social platform; and calculating a contribution ROI experienced by the client as a result of the contribution to the social platform.

Abstract: Multivariate graphs specific to a company's performance, alone or in relation to a benchmark, and methods for producing same include defining on a display screen an origin having a first value, extending from the origin at least three axes on the display screen, the axes being generally equidistant from each other and representing a respective variable, plotting on the display screen a value of each variable concerning the company as a point on a respective axis, and using the plotted points to interpolate first segments between the axes on the display screen. Benchmark information, extrinsic to the company, can be obtained, processed into a rating in the same manner as the company data, and superimposed for ready visual comparison of the company's performance to the obtained benchmark. The benchmark information, if shown, is distinguished from the company's performance graph.

Abstract: Techniques for determining value of a home by applying one or more neural network models to images of spaces in the home. The techniques include: obtaining at least one image of a first space inside or outside of a home; determining a type of the first space by processing the at least one image of the first space with a first neural network model; identifying at least one feature in the first space by processing the at least one image with a second neural network model different from the first neural network model and trained using images of spaces of a same type as the first space; and determining a value of the home at least in part by using the at least one feature as input to a machine learning model different from the first neural network model and the second neural network model.

Abstract: In some aspects, a computing system can detect synthetic identities based on attributes associated with online entities. The computing system can generate entity links between primary entity objects and a secondary entity object. The secondary entity object identifies a target consumer as a secondary entity for accounts identified by the primary entity objects. Attributes of the secondary entity object and attributes of the primary entity objects can be calculated and compared to determine an inconsistency between a combination of a name attribute value and an address attribute value of the secondary entity object as compared to the primary entity objects. A fraud warning indicating that the target consumer is likely to be a synthetic identity can be generated based on the inconsistency and other attributes of the target consumer, such as an inquiries attribute, a terminations attribute, a duration attribute, and so on.

Abstract: Techniques are provided for customer service ticket prioritization using multiple time-based machine learning models. One method comprises obtaining a customer service ticket; collecting, in response to the obtaining, features related to the customer service ticket comprising dynamic information regarding activities performed to address the customer service ticket and textual information describing the customer service ticket; applying the collected features to one of multiple machine learning models to obtain a distress score indicating a likelihood that the customer service ticket will become a distressed customer service ticket, wherein the multiple machine learning models each correspond to different time periods and are trained on historical data and the collected features are applied to the one machine learning model based on an age of the customer service ticket; and processing multiple customer support tickets based on the distress score.

Abstract: A system and methods for evaluating whether a public review matches another review is disclosed. The method includes obtaining a private review and a public review of a business. A likelihood the public review matches the private review is evaluated. The evaluation includes evaluating a match distance between text bodies, reviewer names, review dates and ratings in the public review and the private review. Evaluation rules are applied to determine the likelihood of a match.

Abstract: A blockchain-based method for document transformation and accountability is provided. Document templates for real property transfer are maintained. Each template includes data fields. Some of the document templates are collected as transaction documents for a transaction for the property transfer. The data fields are populated with received data values. Compliance checking is performed on the populated data values. The checked transaction documents are provided to a network having a first tier of network nodes and a second tier of supernodes. One of the supernodes is selected to validate the transaction documents. The validated transaction documents are added to a ledger of transactions. A hash of the validated transaction documents is transmitted to the first tier. One of the network nodes is selected to commit the hash to a blockchain of the first tier. The hash is committed to copies of the blockchain.

Abstract: A computer-implemented method, computer program product, and computing system for receiving a social platform inquiry from a client; defining one or more client identifiers for the client; defining one or more identity-based conditions of the client based, at least in part, upon the one or more client identifiers; and recommending one or more social platforms based, at least in part, upon the one or more identity-based conditions.

Abstract: There is provided a method and system for managing electronic messages in a closed network. Both the method and system include determining a quantity of credits to be expended for a transmission of each electronic message from a device in the closed network; and deducting the quantity of credits from a sender's account at a central credit repository. Preferably, the quantity of credits to be expended is dependent on an identity of a recipient of the electronic message. The identity of the recipient of the electronic message may preferably be associated with the recipient's position in an organizational hierarchy.

Abstract: A set of learner data associated with a learner is received. The set of learner data includes at least a real-time data stream, e.g., derived from instrumentation, in a social network enabled digital learning environment. Based on the set of learner data, at least one learning improvement strategy is determined for improving the learner's learning capability. Atomic level mentorship activities are generated. Each atomic level mentorship activity is targeted with a specific skill and knowledge item and having an estimated duration period. At least one mentorship is identified from at least one social network platform. An initial incentive structure comprising at least an amount of payment and payment modality is created. The atomic level mentorship activities with the initial incentive structure are presented.