Abstract: Disclosed are method and systems to program a server to identify the value of a fund comprising shares of multiple private entities. The server receives transaction data associated with a fund where the transaction data identifies a proportion of shares within the fund associated with each private entity, price per share of each private entity, and other relevant data. The server then executes multiple artificial intelligence models to identify comparable public entities to each private entity. The server then retrieves stock price data for each public entity and calculates a value for each private entity in real time. The server also displays a value of the fund in real time where identification of each private entity is anonymized.

Abstract: Systems and methods for remote huddle collaboration are disclosed. The huddle collaboration system may include a huddle management system which may include an authentication module, a data processing module, and a module manager, among other components. Huddle collaboration system may allow huddle members of a company to fully engage in remote huddle sessions through different kind of client computing devices, in a consistent way regardless of their location. The system may act as an alternative to traditional whiteboards, displaying, collecting, and storing information during an active huddle session, where this information may be available to the users in the form of one or more standard and/or custom sub-applications, according to the user's and/or project's requirements.

Abstract: A suite of fluidless predictive machine learning models includes a fluidless mortality module, smoking propensity model, and prescription fills model. The fluidless machine learning models are trained against a corpus of historical underwriting applications of a sponsoring enterprise, including clinical data of historical applicants. A data appended procedure supplements historical applications data with public records and credit risks. Various features of this data are engineered for improved predictive characteristics. Fluidless models are trained by application of a random forest ensemble including survival, regression and classification models. The trained models produce high-resolution, individual mortality scores. A fluidless underwriting protocol runs these predictive models to assess mortality risk and other risk attributes of a fluidless application that excludes clinical data to determine whether to present an accelerated underwriting offer.

Abstract: A system may include a processor configured to receive a first set of data indicating a first period of time during which a item has a first status, and a second period of time during which the item has a second status. The processor may generate, based on the first set of data, a second set of data containing a plurality of logical rows, each indicating an encoded value of the first status of the item and an encoded value of the second status of the item during a respective period of time that is smaller than or equal to each of the first period of time and the second period of time. The processor may cause a display to present, based on the first set of data and the second set of data, statistical information of the first status and the second status during a third period of time.

Abstract: Methods and systems disclosed herein describe a server that generates an artificial intelligence model comprising a neural network corresponding to at least two sets of data points corresponding to a first independent variable and each data point within a second set of data points corresponding to a second variable dependent upon a corresponding first variable; executes a clustering algorithm to generate a plurality of clusters corresponding to at least one data point within the set of data points; generates a training dataset comprising a third set of data points corresponding to a pairwise distance between each two data points within at least one cluster; and trains the artificial intelligence model based on the training dataset, wherein when the trained artificial intelligence model is executed, the artificial intelligence model identifies a distance between the new data point and at least one data point within at least one cluster.

Abstract: Disclosed herein are embodiments of systems, methods, and products comprises an analytic server for electronic requests routing and distribution. The server receives a plurality of requests from a plurality of electronic user devices. Aiming to routing the plurality of requests to appropriate agents, the server trains an artificial intelligence model for each agent based on historical data. For each request, the server executes the artificial intelligence model to determine a score indicating the probability of the agent converting the request to a successful sale. The server determines an entropy value for each request based on the scores and order the requests into a queue based on the entropy values. The server also calculates a capacity for each agent based on historical agent data. For each request in the queue, the server routes the request to an agent based on at least one of the score and capacity of the agent.

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: A system may generate all possible character mistakes in a first uniform resource locator associated with a first website, which may produce a set of unique and similar uniform resource locators associated with a set of similar websites. The system may execute machine vision algorithms to compare visual images of the first website and the set of similar websites, and identify a subset of similar websites, which may be undistinguishable from the first website. The system may block the subset of websites, and thereby prevent any user from accessing these fraudulent and malicious websites.

Abstract: Systems and methods for improving computational efficiency of data processing and storage are disclosed. The system can identify computing devices capable of performing a data transformation process on a data feed of a data repository, and determine an amount of computational resources needed to perform the data transformation process on the data feed based on attributes of the data feed and computational resources used to process historic processing jobs associated with the data feed. The system can dynamically provision, while performing the data transformation process, a subset of the computing devices based on the amount of computational resources, and execute the data transformation process at the subset of the plurality of computing devices to process the data feed. The system can dynamically re-provision the subset of the plurality of computing devices based on a change in the attributes of the data feed.

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

Abstract: A call management system of a call center identifies an inbound caller based upon computer analysis of customer identifiers, which may include at least two of customer name, street address, and zip code. Approximate string matching analysis matches n-grams generated from strings within customer identifiers, with n-grams generated from customer identification fields while searching one or more databases. Approximate string matching can incorporate a closeness metric based on Jaccard distance, and a Gaussian mixture model of best matches. In one embodiment, a Polymr search engine analyzes customer identifiers of inbound callers to retrieve customer data, such as customer demographic data, matched to the customer identifiers. In another embodiment, the Polymr search engine analyzes customer identifiers of inbound callers to identify repeat callers and retrieve previously collected customer data.

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: An artificial intelligence (AI) model, using logistic regression and gradient boosting tree, may determine a priority score for a user. The priority score may be associated with a likelihood of redemption of investment funds of the user by the user. Based on the priority score for the user, a server may prioritize transmission of a communication message to the user via one of a plurality of communication channels. The communication message may describe why the user should continue with their investment funds without redemption.

Abstract: A computerized system and method may include, in response to receiving a blockchain via a communications network that includes information associated with an event, parsing, by a blockchain parsing engine being executed by a blockchain node, the information to identify a status state of an item related to the event. The blockchain may be inclusive of the information along with the status state of the item may be stored in a storage unit. An event tracking engine may determine from the parsed information that the status state of the item transitioned from a first state to a second state. Responsive to the event tracking engine determining that a qualifying state is satisfied by the item being in the second state, automatically executing, by the blockchain node, a smart code inclusive of initiating communications between a first party and a second party.

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: A computer implemented method for safe, efficient, and fraud-proof continuous retrieval of health data is disclosed. The method comprises receiving a request to update a record associated with a user blockchain comprising identification information associated with a health tracker, a health tracker server, and user authentication data; generating an instruction to receive user data based on the identification information and user authentication data; receiving health data from the health tracker server; retrieving and verifying the validity of the user's latest blockchain; storing the data in a volatile memory; and creating a new block instance corresponding to the data.

Abstract: Methods and systems for developing profitable convertible term products are disclosed. The methods include the disaggregation of the pricing of existing term products and the use of big data analytics to identify opportunities to improve the acceptance of the product within a particular share of the market. Then, a pricing model and a selling model are built to test the product.

Abstract: Disclosed are method and systems to program a server to identify the value of a fund comprising shares of multiple private entities. The server receives transaction data associated with a fund where the transaction data identifies a proportion of shares within the fund associated with each private entity, price per share of each private entity, and other relevant data. The server then executes multiple artificial intelligence models to identify comparable public entities to each private entity. The server then retrieves stock price data for each public entity and calculates a value for each private entity in real time. The server also displays a value of the fund in real time where identification of each private entity is anonymized.

Abstract: An underwriting estimator predictive machine learning model receives as inputs a limited number of details about an applicant, and outputs an immediate underwriting estimate of risk class. A preliminary pre-screening review redirects applicants with one or more screening impairments to a human-in-the-loop quick quote process. Model inputs include estimator inputs data that are pre-selected from the dataset of impairments data after excluding the screening impairments from the dataset of impairments. The underwriting estimator model may incorporate alternative pathways that output individualized underwriting estimates for some applicants and cohort-level marginal distributions for other applicants. Model outputs also include explanation files providing interpretability of underwriting estimates. The explanation files may include additive feature attribution data and rule based natural language explanations.