Abstract: Systems and methods described herein can automatically route an inbound call from an identified customer to one of a plurality of agents, the agent being selected on the basis of likelihood of a favorable outcome. The method determines a predictive model appropriate for the identified customer, with model variables including call center data, and targeted marketing data based upon risk data for the customer. An analytical engine calculates outcome predictions by applying the predictive model to values of model variables over a recent time interval. In a time-series analysis, this calculation is repeated while dynamically adjusting the recent time interval, until identifying a call routing option that satisfies a favorable outcome criterion. This method may be used to select the agent to handle the incoming call, and optionally to select a product for that agent to discuss with the identified customer.

Abstract: Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which dynamically predicts future events for web users. The analytic server generates prediction models based on historical click-through analytics data received from the web server. The analytic server captures the current event (e.g., the current operation of the web user) on the web page, and determines the next event by predicting the web user behavior using the prediction models on an event-by-event basis. The analytic server also queries the web user data from a database to better understand the web user's intention, and improve the prediction accuracy. The analytic server modifies the HTML code to display the web page to include a graphical user interface comprising the predicted event. Based on the web users' reactions to the predicted event, the analytic server updates the prediction models.

Abstract: This disclosure discloses systems, devices, and methods for parallelized data structure processing in context of machine learning and reverse proxy servers.

Abstract: Disclosed is a method and a system for efficiently and accurately processing air particulate datasets when facing a high number of air particulate datasets from multiple locations to generate an artificial intelligence model having one or more computer-based rules that determines eligibility of a user to avail a health-related service based on air particulate records associated with current and past locations of the user.

Abstract: Systems and methods for assessing the needs of customers using predictive modeling techniques are disclosed. The method receives customer data from a first database and provided by the user. The method generates an instruction to a second database and receives additional customer information received from external databases to generate a basic profile for data based on the customer. The system further analyzes data provided by the user. The method generates a customer profile based on the basic customer data and additional data. The method determines missing data from the customer profile associated and a set of attributes of the user. The method identifies a profile with the customer similar set of attributes and estimates the missing data using predictive modeling techniques to generate estimated customer information. The system further pre-populates one or more missing fields of the full profile associated with the customer based on said estimated customer information. The system.

Abstract: A call management system of a call center retrieves from a customer database enterprise customer data associated with an identified customer in a customer call, which may include customer event data, attributions data, and activity event data. The customer database tracks prospects, leads, new business, and purchasers of an enterprise. The system retrieves customer demographic data associated with the identified customer. A predictive model is selected from a plurality of predictive models based on retrieved enterprise customer data. The selected predictive model, including a logistic regression model, and tree-based model, determines a value prediction signal for the identified customer, then classifies the identified customer into a first value group or a second value group. The system routes a customer call classified in the first value group to a first call queue assignment, and routes a customer call classified in the second value group to a second call queue assignment.

Abstract: Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which determines user health attributes by tracking the user’s behaviors and activities within a predetermined space. The analytic server receives tracking data from a set of sensors installed in the predetermined space. The sensors track a beacon worn by the user. The analytic server determines micro-locations and user behaviors based on the tracking data. The analytic server determines the coordinates of the sensors based on the sensor identifiers and maps the coordinates to regions by referring to a floor plan map. The analytic server determines the user behaviors and activities by aggregating the micro-locations and regions the user visited at different time. The analytic server determines the user’s health score based on the micro-locations and user behaviors by executing an artificial intelligence model. The analytic server determines a recommendation of premium based on the health score.

Abstract: A system herein provides automated call-back of customers who have terminated an inbound call by exercising a call-back option of an interactive voice response unit or by abandoning the inbound call, using predictive modeling of caller value to prioritize call-backs. The call management system monitors the inbound customer call and detects any termination of the customer call. A call-back module opens a call-back record for the terminated customer call and associates that call-back record with an identified customer. The call-back module retrieves customer demographic data and other data associated with the identified customer. A predictive module determines a value prediction signal for the identified customer by modeling purchase and lapse behaviors and classifies each identified customer for either priority call-back or subordinate call-back treatment.

Abstract: Systems and methods described herein can automatically route an inbound call from an identified customer to one of a plurality of agents, the agent being selected on the basis of likelihood of a favorable outcome. The method determines a predictive model appropriate for the identified customer, with model variables including call center data, and targeted marketing data based upon risk data for the customer. An analytical engine calculates outcome predictions by applying the predictive model to values of model variables over a recent time interval. In a time-series analysis, this calculation is repeated while dynamically adjusting the recent time interval, until identifying a call routing option that satisfies a favorable outcome criterion. This method may be used to select the agent to handle the incoming call, and optionally to select a product for that agent to discuss with the identified customer.

Abstract: A call management system of a call center retrieves from a customer database enterprise customer data associated with an identified customer in a customer call, which may include customer event data, attributions data, and activity event data. The customer database tracks prospects, leads, new business, and purchasers of an enterprise. The system retrieves customer demographic data associated with the identified customer. A predictive model is selected from a plurality of predictive models based on retrieved enterprise customer data. The selected predictive model, including a logistic regression model, and tree-based model, determines a value prediction signal for the identified customer, then classifies the identified customer into a first value group or a second value group. The system routes a customer call classified in the first value group to a first call queue assignment, and routes a customer call classified in the second value group to a second call queue assignment.

Abstract: Embodiments disclosed herein disclose a back-end computer to generate a risk score and a front-end visualization engine to hierarchically display the generated risk core. The back-end computer users a machine learning model for a stepwise perturbation from a digital reference profile until a user profile to be score is reached. The computer may calculate intermediate risk score for each perturbation and calculate the final risk score after all the perturbations are completed. The front-end visualization engine generates an interactive hierarchical display showing information associated with the risk score calculation. More specifically, the visualization engine may show a filtered list of users sharing one or more attributes with the user profile, a visual rendering of the top factors contributing to the risk score, and individual input values within a factor; and juxtapose the scores and attributes of the user profile in the graphical information display of the associated population.

Abstract: This disclosure discloses systems, devices, and methods for parallelized data structure processing in context of machine learning and reverse proxy servers.

Abstract: Embodiments of systems and methods for fraud review are disclosed. The systems may comprise multi-tiered computing systems which may receive fraud alerts from multiple sources. A computing system in a tier may receive a fraud alert and use one or more fraud risk metrics to determine whether the fraud alert should be escalated. If the computing system determines that the fraud alert should be escalated, the computing system may transmit an escalation message to a higher tier computing system. If the computing system determines that the fraud alert should not be escalated, the computing system may transmit a message to a fraud prevention computing system. In some embodiments, the computing system may determine that the fraud alert is a false positive and transmit a false positive message to the source of the fraud alert such as a lower tier computing system.

Abstract: Disclosed herein are embodiments of systems, methods, and products comprises an analytic server, which dynamically predicts future events for web users. The analytic server generates prediction models based on historical click-through analytics data received from the web server. The analytic server captures the current event (e.g., the current operation of the web user) on the web page, and determines the next event by predicting the web user behavior using the prediction models on an event-by-event basis. The analytic server also queries the web user data from a database to better understand the web user's intention, and improve the prediction accuracy. The analytic server modifies the HTML code to display the web page to include a graphical user interface comprising the predicted event. Based on the web users' reactions to the predicted event, the analytic server updates the prediction models.

Abstract: Methods and systems for determining relationships between two or more nominally unrelated data sources utilizing a combination of probabilistic modeling and graphical clustering are described. The systems and methods for utilizing probabilistic model functions as a way of determining and judging the likelihood that two records from different systems are related to the same entity.

Abstract: This disclosure discloses systems, devices, and methods for parallelized data structure processing in context of machine learning and reverse proxy servers.

Abstract: A system and method for automated body mass index is disclosed. The disclosed method operates within a system architecture including one or more computing devices, one or more servers, and one or more databases. A processor operating within the one or more servers executes one or more algorithms for detecting relevant features associated with a potential client's multimedia information. The method may include calculating feature values, such as abdomen circumference, face width, face height, cheekbone width, jaw width, and neck width, and the like as well as calculating the body mass index of the potential client using one or more regression algorithms. A baseline and updated BMI may be determined, and used for determining a baseline and updated value.

Abstract: A call management system of a call center retrieves from a customer database enterprise customer data associated with an identified customer in a customer call, which may include customer event data, attributions data, and activity event data. The customer database tracks prospects, leads, new business, and purchasers of an enterprise. The system retrieves customer demographic data associated with the identified customer. A predictive model is selected from a plurality of predictive models based on retrieved enterprise customer data. The selected predictive model, including a logistic regression model, and tree-based model, determines a value prediction signal for the identified customer, then classifies the identified customer into a first value group or a second value group. The system routes a customer call classified in the first value group to a first call queue assignment, and routes a customer call classified in the second value group to a second call queue assignment.

Abstract: Systems and methods for assessing the needs of customers using predictive modeling techniques are disclosed in which a server receives, from a computing device, a request to generate a recommendation for a first user, the server further receiving a set of attributes of the first user; identifies at least one missing attribute for the first user and an existing user profile corresponding to a second user having the set of attributes; executes an artificial intelligence model trained based on personas corresponding to a set of existing users, wherein the artificial intelligence model estimates the at least one missing attribute of the first user; updates a user profile of the first user using the estimated at least one missing attribute generated by the artificial intelligence model; generates the recommendation based on the updated user profile; and transmits the recommendation to be displayed on the graphical user interface.

Abstract: Systems and methods described herein can automatically route an inbound call from an identified customer to one of a plurality of agents, the agent being selected on the basis of likelihood of a favorable outcome. The method determines a predictive model appropriate for the identified customer, with model variables including call center data, and targeted marketing data based upon risk data for the customer. An analytical engine calculates outcome predictions by applying the predictive model to values of model variables over a recent time interval. In a time-series analysis, this calculation is repeated while dynamically adjusting the recent time interval, until identifying a call routing option that satisfies a favorable outcome criterion. This method may be used to select the agent to handle the incoming call, and optionally to select a product for that agent to discuss with the identified customer.