Abstract: Embodiments relate to system for automatically predicting payer response to claims. In an embodiment, the system receives claim data associated with a claim. The system identifies a set of claim features of the claim data, and generates an input vector with at least a portion of the set of claim features. The system applies the input vector to a trained model. A first portion of the neural network is configured to generate an embedding representing the input vector with a lower dimensionality than the input vector. A second portion of the neural network is configured to generate a prediction of whether the claim will be denied based on the embedding. The system provides the prediction for display on a user interface of a user device. The prediction may further include denial reason codes and a response date estimation to indicate if, when, and why a claim will be denied.
Type:
Grant
Filed:
June 29, 2021
Date of Patent:
January 2, 2024
Assignee:
AKASA, Inc.
Inventors:
Byung-Hak Kim, Hariraam Varun Ganapathi, Andrew Atwal
Abstract: A system for training a learning machine accesses a training database of reference metadata that describes reference plans that include reference first-type plans and reference second-type plans. Such plans may be travel plans or other plans. The system trains the learning machine to distinguish candidate first-type plans from candidate second-type plans. The training of the learning machine is based on a set of decision trees generated from randomly selected subsets of the reference metadata, and the randomly selected subsets each describe a corresponding randomly selected portion of the reference plans. The system then modifies the trained learning machine based on asymmetrical penalties for incorrectly distinguishing candidate first-type plans from candidate second-type plans. The system then provides the modified learning machine for run-time use in classifying plans.
Type:
Grant
Filed:
July 15, 2019
Date of Patent:
January 2, 2024
Assignee:
Hipmunk, Inc.
Inventors:
Bharat Sri Vardhan Vemulapalli, Eric Etu, Marguerite Ellis
Abstract: A computer-implemented method comprises linking a private AI model to a public AI model to thereby form a combined AI model comprising the private AI model and the public AI model; and training the combined AI model with private samples while keeping the public AI model fixed so that only the private AI model is trained with the private samples.
Type:
Grant
Filed:
May 16, 2019
Date of Patent:
January 2, 2024
Assignee:
International Business Machines Corporation
Abstract: The invention relates to implementing rules based authentication for credit card transactions. The system and method may involve: receiving a transaction request associated with a card product from a user at a point of sale system; determining an authorization mode for the transaction request based on one or more transaction attributes; executing an authentication rule for the transaction request; transmitting an authentication request via the authorization mode based on the authentication rule; requiring an authorization input from the user responsive to the authentication request; and upon receiving a proper authentication input, verifying the user and proceeding with the transaction request.
Abstract: Systems and methods are provided for processing a group of essays to develop a classifier that detects nonsensical computer-generated essays. A data structure associated with a group of essays is accessed, wherein the group of essays includes nonsensical computer-generated essays and good-faith essays. Both the nonsensical computer-generated essays and the good-faith essays are assigned feature values. The distribution of feature values between the nonsensical computer-generated essays and the good-faith essays is measured. A classifier that detects whether an essay is a nonsensical computer-generated essay is developed, wherein the classifier is developed using the distribution of feature values.
Type:
Grant
Filed:
July 1, 2019
Date of Patent:
December 26, 2023
Assignee:
Educational Testing Service
Inventors:
Aoife Cahill, Martin Chodorow, Michael Flor
Abstract: Eye gaze measurements are used to give input to a surgical robotic system. Eye tracking input is enhanced using a pair of eye trackers positioned to track the gaze of a user observing an endoscopic image on a display. At least one of the eye trackers is moveable relative to the display in a horizontal and/or vertical direction relative to the image display.
Abstract: A distributed computing system facilitates automatic loan agreements between syndicate participants. The system includes a blockchain comprising circuitry embodying a plurality of blockchain services. A membership service registers participants to the syndicate, generates a unique identifier for each of the participants, and verifies that a respective entity is a node on the blockchain. An oracle service retrievably stores loan terms templates provided by the participants via a centrally managed entity. A smart contracts service receives financial and/or geo-location data associated with the plurality of syndicate participants. A predictive analytics service uses the data to determine whether a first syndicate participant has an excess of funds and whether a second syndicate participant has a lack of funds. A loan service automatically facilitates a loan agreement between the first participant and the second participant.
Type:
Grant
Filed:
January 12, 2021
Date of Patent:
December 26, 2023
Assignee:
Wells Fargo Bank, N.A.
Inventors:
Andrew J. Garner, IV, Chris Theodore Kalaboukis, Rameshchandra Bhaskar Ketharaju, Joon Maeng, Ramanathan Ramanathan, Abhijit Rao, Andres J. Saenz
Abstract: A network computing system to provide an account management service for guiding user actions and providing users with information to facilitate decision making. In providing the account management services, the network computer system makes predictive determinations about the actions of service providers, in connection with specific actions of individual users.
Type:
Grant
Filed:
January 30, 2020
Date of Patent:
December 26, 2023
Assignee:
Freedom Financial Network, LLC
Inventors:
Michael Woodward, Jon Pedley, Jason Pack, John McCormick, Ryan Sepiol
Abstract: Described herein is an identity network for authenticating a user for a relying party and providing access to the user's credit report. The identity network may receive an unlock request for the digital identity and credit report of a user from a relying party. In response, the identity network may provide an identity provider link for accessing the identity provider application. The user may login to the identity provider application and provide consent for obtaining the user's credit report. The identity provider provides the identity network with verification of the digital identity of the user and the consent response from the user. The identity network can request access from a credit reporting agency and receive a credit report key in response. The identity network can provide the credit report key to the relying party, which can use the key to access the user's credit report from the credit reporting agency.
Type:
Grant
Filed:
April 8, 2022
Date of Patent:
December 19, 2023
Assignee:
Early Warning Services, LLC
Inventors:
Gregory Slowiak, Eric Woodward, Philip Lam, Jeff Shultz
Abstract: The present invention teaches a system, method and computer program for enabling local or regional merchants to participate in an automated cause marketing (ACM) program using mobile devices. The ACM program that may provide benefits to several parties involved in fundraising for one or more supported organizations, including one or more supported organizations, advertising providers, merchants, and individuals. Merchants are able to access enhanced analytics regarding their transactions with members and non-members of the ACM program and can use these enhanced analytics to realize an increased number of or revenue from transactions with members. The present invention also teaches a system and method for enabling advertising providers to acquire and analyze data associated with consumers-merchant transactions. The present invention provides the above features optimally using mobile devices.