Abstract: A novel technique for matching, merging, and combining a new database record with a master database record is described herein. The technique uses specific fields to compare in a unique exact match and fuzzy match combination to determine if a non-exact matching record pair is indeed a matched pair. Once the match is established, the records are merged or combined to utilize the best information from the two records.

Abstract: A legal spend management solution is described herein, a solution that utilizes improved machine learning algorithms to match lines of a legal invoice to lines in a receipt from a set of receipts. The matching uses cosine similarity algorithms and Levenshtein distances to determine whether there is a match between the receipt and the invoice lines. The machine learning results are displayed using a novel set of icons that present the confidence score with a set of three squares below a document icon.

Abstract: A unique system for data visualization of invoice data and financial information on a graphical user interface is described herein. The system comprises of a visual display for invoices, the transactional data regarding these invoices, and the processing of those invoices. The visual display includes a timeline with vertical bars emanating from it, wherein these vertical bars correspond to groupings of invoice data based on user inputted and automated computer inputted information. Users input a start date for the timeline or an amount of elapsed days for the timeline. The timeline includes displaying matched and outstanding invoice data, wherein the visualization allows users to view graphically the interaction between them.

Abstract: Disclosed is a system and a method for verifying a user using reality applications. The system includes a database for storing plurality of modules, a server coupled to the database for processing the stored plurality of modules, a reality glasses having a camera to capture movements of the user, and a reality display coupled to the server to overlay virtual objects and the processed plurality of modules onto a field of view of the user, wherein the plurality of modules authenticates the user to access at least one of the virtual objects. The plurality of modules includes a biometric module performs a first level verification by performing biometric scans on the user, using the reality camera, a signature module performs a second level verification by verifying signature of the user drawn in air captured by the reality camera, and a signature motion flow module performs a third level verification by verifying flow of the user's signature captured by the reality camera.

Abstract: A novel distributed method for machine learning is described, where the algorithm operates on a plurality of data silos, such that the privacy of the data in each silo is maintained. In some embodiments, the attributes of the data and the features themselves are kept private within the data silos. The method includes a distributed learning algorithm whereby a plurality of data spaces are co-populated with artificial, evenly distributed data, and then the data spaces are carved into smaller portions whereupon the number of real and artificial data points are compared. Through an iterative process, clusters having less than evenly distributed real data are discarded. A plurality of final quality control measurements are used to merge clusters that are too similar to be meaningful. These distributed quality control measures are then combined from each of the data silos to derive an overall quality control metric.

Abstract: Disclosed is an apparatus for matching a payment received from a remitter for two or more invoices generated by a beneficiary against invoices of two or more customers associated with the remitter. The apparatus includes a storage unit for storing a plurality of computer program instructions, a graphical user interface for displaying a graphical output, and a processing unit for processing the plurality of computer program instructions. The plurality of computer program instructions includes a payment receive module to receive a payment from the remitter, a total amount module to display the total amount received from the remitter, a customer account module to display a list of invoices generated by the beneficiary against the customers associated with the remitter, and a split payment module to split the total amount into multiple split amounts. Each split amount matches the amount on at least one customer's invoice, and the total amount matches the sum of amounts on two or more customer's invoices.

Abstract: A method for securing data by embedding the data in a data structure and utilizing a sensor device to detect transfer of the data structure. The data is embedded such that the data is only accessible by first executing an executable program. If the executable program determines that the device attempting to access the data (the accessing device) does not have permission to access the data, then the executable program destroys all or a portion of the data. If the data structure is transferred to another device, a sensor device positioned to detect the data structure when transferred will identify the data. If the sensor device determines that the data structure is not permitted to be transferred, then the sensor device destroys all or a portion of the data.

Abstract: A system, method and apparatus for providing a global service for securely storing deposit instructions is described. The service provides payment processing services with a central location to translate payee information into a revocable d-token that represents the payee deposit instructions. A second service allows qualified banking institutions to convert the d-token into deposit instructions to effectuate a funds transfer.

Abstract: Disclosed is a system for scoring customers of a financial institution based on financial data. The system includes a central database that stores a plurality of modules, a central server that processes the plurality of modules and a display unit that displays the processed plurality of modules. The plurality of modules includes a criteria configuration module, a data module, and a computation module. The criteria configuration module includes a metric module to receive the input parameters required to evaluate the score, and a measurement module for defining transformation criteria to be applied on the data corresponding to the input parameters. The computation module includes a metric evaluation module to compute and applies the transformation criteria to the values of the input parameters, and a scoring module coupled to the metric evaluation module to automatically compute and display the score of the customers based on the values retrieved from the metric evaluation module.

Abstract: A unique implementation of a machine learning application for suggesting actions for a user to undertake is described herein. The application transforms a history of user behavior for a plurality of users into a set of models that represent user actions, and the optimal actions, given a set of parameters. These models are then used to suggest that users in a payments or banking environment take certain actions based on a best in class model derived from the best performing user. The models are created using the DensiCube, random forest, K-means or other machine learning algorithms.

Abstract: A novel opposing polarity machine learning device and method is described, where two machine learning models are generated, one for each polarity (accepting and rejecting, for example). The device may include memory, connected to circuitry, the memory including historical records of opposing polarities, an input record received from an input device, and instructions for the circuitry.

Abstract: A novel distributed method for machine learning is described, where the algorithm operates on a plurality of data silos, such that the privacy of the data in each silo is maintained. In some embodiments, the attributes of the data and the features themselves are kept private within the data silos. The method includes a distributed learning algorithm whereby a plurality of data spaces are co-populated with artificial, evenly distributed data, and then the data spaces are carved into smaller portions whereupon the number of real and artificial data points are compared. Through an iterative process, clusters having less than evenly distributed real data are discarded. A plurality of final quality control measurements are used to merge clusters that are too similar to be meaningful. These distributed quality control measures are then combined from each of the data silos to derive an overall quality control metric.

Abstract: This document describes a non-transitory computer readable media programmed to enrich an entered record submitted to be matched with a dataset record stored on a data storage device. The enrichment is done by supplementing data in the entered record with customer data from a dataset. The media is further programmed to search through a plurality of dataset records in the dataset for the entered record. The search is programmed to first determine if the entered record unambiguously matches one of the dataset records or if the entered record unambiguously does not match one of the dataset records. If the entered record does not unambiguously match one of the dataset records, score match characteristics using a Fellegi-Sunter algorithm, save the score as a highest score if the score is above the highest score less a threshold, and save a location of one of the dataset records as a matching record if the score is above a previous highest score.

Abstract: A method of exercising effective influence over future occurrences using knowledge synthesis is described. Techniques include influencing methods that yield actions, once a proposed outcome has been assumed. This is different from methods, typically referred to as “predictive” or “prescriptive” that use analytics to model future results based upon existing data and predict most likely outcome. One or more methods of analysis of historical data, in a hierarchical manner, determine events which led to an observed outcome. The outcome-based algorithms use, as input, a future event or state and generate attributes that are necessary precursors. By creating these attributes, the future can be affected. Where necessary, synthetic contributors of such attributes are also created and made to act in ways consistent with generating the assumed outcome. These contributors might be called upon respectively, to post favorable opinions, to report balmy weather, or to describe sales to a certain population demographic.

Abstract: A two-step algorithm for conducting near real-time fuzzy searches of a target on one or more large data sets is described. This algorithm includes the simplification of the data by removing grammatical constructs to bring the target search term (and the stored database) to their base elements and then performing a Levenstein comparison to create a subset of the data set that may be a match. Then performing a scoring algorithm while comparing the target to the subset of the data set to identify any matches.

Abstract: A unique user interface for improving legal (and other fields) spend management is described herein. The algorithm may include looping through the lines of an invoice and displaying an icon with multiple visual indicators displaying the machine learning confidence score. When a mouse hovers over the icon, a set of icons are displayed to accept the teaching user's input. In addition, the words that drove the machine learning confidence score are highlighted with formatting so that the teaching user can understand what drove the machine learning confidence score.