Capital One Services, LLC

Jennifer Kwok

Abhay Donthi

Joshua S Edwards

Viraj Chaudhary

Tania Cruz Morales

Sara Rose Brodsky

Jason Zwierzynski

Salik Shah

Dwij Trivedi

Leeyat Bracha Tessler

Cruz Vargas

Abdelkader M'Hamed Benkreira

Tyler Maiman

Sarah Jane Cunningham

Zviad Aznaurashvili

Vyjayanthi Vadrevu

Xiaoguang Zhu

Alexander Lin

Daniel Miller

Abdelkader M'hamed Benkreira

Cameron Noah

Lisa Guo

Susan Hogan Davis

Martin Figueroa-Ramirez

Tara Ann Hickey

Albert Hergenroeder

Systems and methods for external account authentication are disclosed herein. They include receiving a call to pair the external account with a secure account, extracting external data from the external account, the external data corresponding to external account content, providing user activity data from the secure account as an input to an authentication machine learning model, providing the external data as an input to the authentication machine learning model, the authentication machine learning model configured to output a certainty level that the external account is associated with a user of the secure account based on the external data and the activity data, receiving the certainty level from the authentication machine learning model, determining that the certainty level meets a certainty threshold, and pairing the external account with the secure account based on determining that the certainty level meets the certainty threshold.

Systems and methods for external account authentication

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving a notification to engage a transmission guard bot in a communication session; generating a trained transmission guard bot configured with communication capabilities to engage the communication session; engaging the trained transmission guard bot into the communication session between the plurality of computing devices associated with the plurality of users; utilizing the trained transmission guard bot to continually monitor a plurality of content data associated with the communication session for a predetermined period of time; detecting a suspicious content data point within the plurality of content data associated with the communication session based on the continual monitoring of the at least one transmission guard bot; determining a risk assessment metric associated with the communication session; and invoking an action related to spam prevention via the at least one trained transmission guard bot.

Computer-based systems configured to dynamically enhance a spam prevention functionality on a computing device and methods of use thereof

A method for executing actions based on event data using machine learning is disclosed. The method comprises: receiving occasion data associated with a user; analyzing, using a trained machine learning model, the occasion data to identify an occasion associated with a first classification, wherein the trained machine learning model has been trained based on (i) training occasion data that includes information regarding one or more occasions associated with the training occasion data and (ii) training classification data that includes a prior classification for each of the occasions, to learn relationships between the training occasion data and the training classification data, such that the trained machine learning model is configured to use the learned relationships to identify an occasion associated with a first classification in response to input of the occasion data; determining an action based on the occasion associated with the first classification; and automatically executing the action.

Systems and methods for machine learning based execution of actions based on calendar event data

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving a permission indicator identifying a permission by the first user to detect calls being received by the computing device; receiving an indication of a particular call being received from a second user at a particular phone number; detecting a triggering condition to verify when the particular phone number is associated with the particular entity; instructing the computing device to execute a computer routine to verify when the particular phone number is associated with the particular entity; receiving an indication from the computer routine when the particular phone number is not associated with the particular entity; instructing the computing device to perform at least one security action; and instructing to notify a second computing device associated with the particular entity with information pertaining to the particular call.

Computer-based systems configured for automatic detection of a verified identity related to interaction sessions and methods of use thereof

Systems and methods for detecting and repairing loss of a primary digital communication channel may include a server and a user device. The server may be configured to send a push notification to an application of the user device over a network, receive, in response to the sending of the push notification, push notification status data, apply a predictive model to determine whether the primary digital communication channel has failed based on the push notification and the push notification status data; and transmit, upon a determination that the primary digital communication channel has failed, a communication to the user over one or more alternative digital communication channels.

Systems and methods to determine the loss of ability to notify customer through mobile app and prompt re-download

In some implementations, a front-end device may receive, from a brain-machine interface (BMI) associated with a user, a request to authenticate the user with secret information associated with the user. Accordingly, the front-end device may transmit, to the BMI, a request for an identifier associated with one or more hardware components of the BMI. The front-end device may receive, from the BMI, an indication of the identifier associated with the one or more hardware components. Accordingly, the front-end device may authenticate the user based on the secret information associated with the user and the identifier associated with the one or more hardware components. Additionally, or alternatively, the front-end device may authenticate the user based on a location of an external device associated with the user and/or an indication of a biometric property associated with the user.

Authentication using brain-machine interfaces

Disclosed aspects and embodiments pertain to customer distress assistance. A call can be detected to a callee from a caller. The call can be analyzed and determined to be a fraud or spam risk. In response, callee monitoring is triggered. The monitoring can capture biometrics or speech of the callee. Distress in the callee can be determined through analysis of the biometrics or speech and comparison to reference biometrics or speech of the callee. An individual associated with the callee can be selected based on determining the distress in the customer. The individual can be contacted through a notification or a call to assist the callee in distress.

Customer distress assistance

Systems and methods of the present disclosure enable the generation and use of secure offline tokens for account activity authentication. A processor receives an activity record including activity details including an entity identifier. The processor determines a flight booking associated with the activity record when the entity identifier includes an airline, and determines flight data associated with the flight booking. The processor automatically generates an offline token associated with the user account, including account access restrictions. The account access restrictions include a token activation period that binds the offline token to a duration of the flight, and a token entity binding that binds the offline token to use with the airline for performing in-flight account activity requests. The processor automatically causes a computing device to download the offline token to enabling performing the in-flight account activity requests with the entity during the offline token activation period.

Systems utilizing secure offline limited-use tokens for temporary electronic activity authentication and methods of use thereof

Methods and systems are disclosed herein for using one or more machine learning models to determine whether a user is expected to complete a task or action by a deadline. The one or more machine learning models may be trained and/or used to recommend a communication protocol for sending a reminder to the user such that the user is predicted to be more likely to complete an action by the action's deadline. A computing system may use the one or more machine learning models to generate a recommendation for type of reminder to send, for example, if it is predicted that the user is not expected to complete the task by the deadline. A computing system may determine the message to send, the communication protocol to use, and/or the time to send the message.

Machine learning for determining communication protocols

A computer-implemented method for authenticating a source of a telephone call to a recipient of the telephone call may include receiving, prior to receiving the telephone call, a request to input first authentication information. The first authentication information may include a passcode or a selection of a security question. The method may include receiving input of the first authentication information and sending, by the user device, the first authentication information to a computing device associated with the source of the telephone call. The method may include receiving the telephone call from the source and receiving input from the recipient of the telephone call to answer the telephone call. The method may include receiving second authentication information from the computing device, where the second authentication information may include the passcode or an answer to the security question. The method may include outputting the second authentication information.

Systems and methods for detecting and/or preventing vishing attacks using user-generated authentication information

Disclosed embodiments pertain to determining and communicating purchasing power through a visualization. A trained machine learning model can be invoked on a credit card without a preset limit to predict a dynamic spending limit based on credit card data or credit score data. Purchasing power can be computed as the difference between the dynamic spending limit and a current balance, and a purchase power class can be determined based on the purchasing power. Further, a graphic representation of a purchasing power class can be determined. Subsequently, presentation of the graphic representation can be triggered in a manner that overlays the graphic representation on or around the physical card.

Dynamic purchasing power visualization

In some aspects, a computing system may use machine learning to determine whether a control is faulty or generate recommendations to make a modification to a control. may identify a portion of problematic computer code that implements the faulty control through the use of machine learning. A computing system may use machine learning to generate embeddings that map incident data and control data (e.g., computer-readable code of a control) to the same vector space. Further, a computing system may use a weighting mechanism that may be used to weight each sample used to train a machine learning model, which may allow a model to train more efficiently.

Machine learning for detecting and modifying faulty controls

Systems as described herein may analyze big data to generate predictions for Software-as-a-Service (SaaS) offerings and/or other subscription-based software. A prediction system may receive small business transaction data comprising payment information between a plurality of merchants and a software vendor. The prediction system may receive enterprise merchant insights information. The prediction system may identify, based on the small business transaction data and the enterprise merchant insights information, recurring transactions using a first machine learning model. The prediction system may generate an average contract price and a confidence score, using a second machine learning model. The prediction system may generate a recommendation comprising a renewal rate. Based on a determination that a service provided by the software vendor is coming due for renewal, the prediction system may send, to a particular merchant, an alert associated with the renewal and the recommendation.

Predictions based on analysis of big data

Systems and methods of the present disclosure enable the prediction of activity distribution across mediums of activities by employing processors that receive an activity record history across channels of mediums of activity. A candidate activity channel profile of a future activity channel is received that includes candidate channel attributes including: a medium attribute identifying the medium, and an activity category attribute identifying a category of activities of the future activity channel. Cannibalization forecasting models are used to predict channel metrics based on the candidate channel attributes and model parameters trained on the activity record history. New candidate channel attributes are automatically generated that improve the at least one channel metric based on the at least one channel metric, and a new candidate activity channel profile is automatically modified using the new candidate channel attributes. The channel metrics are displayed on computing devices associated with users.

Systems for predicting activity distribution across mediums and methods thereof

Systems, apparatuses, and methods are described for adjustment of card configurations for flight interruptions. Past flight interruptions that users experienced may be determined. Transactions conducted via the users' payment cards during the past flight interruptions may be determined. The data may be used for determining customized metrics for adjusting card configurations of the payment cards during current flight interruptions. Default metrics for adjusting card configurations of the payment cards during current flight interruptions may be determined. Current flight statuses may be monitored for the users. Current flight interruptions may be detected for the users. Card configurations of the payment cards may be adjusted during the detected current flight interruptions.

Growing community of inventors

New York, NY, United States of America

Jennifer Kwok