Patents by Inventor Christopher Bayan Bruss

Christopher Bayan Bruss has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20240037427
    Abstract: A computing system may generate a first set of importance metrics (e.g., scores or values) for a model. The importance metrics may be generated using an explainable artificial intelligence technique, and an individual importance metric may indicate how influential a corresponding feature is for a decision made by a model. The computing system may determine an important feature and create a modified dataset by removing the important feature from the dataset. The computing system may train the model on the modified dataset and evaluate the performance of the model to determine the effect of removing the feature (e.g., which may indicate how important the feature is to output generated by the model). This process may be repeated for additional features and additional performance metrics may be obtained.
    Type: Application
    Filed: July 26, 2022
    Publication date: February 1, 2024
    Applicant: Capital One Services, LLC
    Inventors: Samuel SHARPE, Christopher Bayan BRUSS, Brian BARR, Sahil VERMA, Jocelyn HUANG
  • Publication number: 20230351788
    Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.
    Type: Application
    Filed: May 19, 2023
    Publication date: November 2, 2023
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Patent number: 11790369
    Abstract: Systems and methods are disclosed herein for improving machine learning of a data set. In one example, the method may include training a predictive model on an initial data set comprising labeled data, wherein the training is performed in an active learning system. The method may further include generating a set of parameters based on the training and introducing an unlabeled data set into the predictive model. According to some embodiments, the method may further include applying the set of parameters to the unlabeled data set, generating a set of predictions associated with the applied set of parameters and calculating a first uncertainty score and a second uncertainty score associated with the generated set of predictions. Moreover, the method may also include modifying the data set based on the first uncertainty score, and modifying the predictive model based on the second uncertainty score.
    Type: Grant
    Filed: September 3, 2020
    Date of Patent: October 17, 2023
    Assignee: Capital One Services, LLC
    Inventors: Jason Wittenbach, James O. H. Montgomery, Christopher Bayan Bruss
  • Patent number: 11694457
    Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.
    Type: Grant
    Filed: June 24, 2022
    Date of Patent: July 4, 2023
    Assignee: Capital One Services, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Publication number: 20220318562
    Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.
    Type: Application
    Filed: June 24, 2022
    Publication date: October 6, 2022
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Patent number: 11386286
    Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.
    Type: Grant
    Filed: April 7, 2020
    Date of Patent: July 12, 2022
    Assignee: Capital One Services, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Publication number: 20220067737
    Abstract: Systems and methods are disclosed herein for improving machine learning of a data set. In one example, the method may include training a predictive model on an initial data set comprising labeled data, wherein the training is performed in an active learning system. The method may further include generating a set of parameters based on the training and introducing an unlabeled data set into the predictive model. According to some embodiments, the method may further include applying the set of parameters to the unlabeled data set, generating a set of predictions associated with the applied set of parameters and calculating a first uncertainty score and a second uncertainty score associated with the generated set of predictions. Moreover, the method may also include modifying the data set based on the first uncertainty score, and modifying the predictive model based on the second uncertainty score.
    Type: Application
    Filed: September 3, 2020
    Publication date: March 3, 2022
    Applicant: Capital One Services, LLC
    Inventors: Jason Wittenbach, James O.H. Montgomery, Christopher Bayan Bruss
  • Publication number: 20220019836
    Abstract: Methods and systems disclosed herein may quantify the content and nature of first streaming data to detect when the typical composition of the first streaming data changes. Quantifying the content and nature of the first streaming data may begin by generating a baseline representation of the content of the first streaming data as represented by a first matrix. Once generated, the first matrix may be used as a control against subsequently received data streams. In this regard, a second matrix may be generated from second streaming data and compared to the first matrix to determine the differences between the first streaming data and the second streaming data. Once a difference is determined, the difference may be compared to a threshold value and, when the difference exceeds the threshold value, an administrator may be notified and corrective action taken.
    Type: Application
    Filed: September 1, 2021
    Publication date: January 20, 2022
    Applicant: Capital One Services, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Patent number: 11138458
    Abstract: Methods and systems disclosed herein may quantify the content and nature of a first stream of text to detect when the typical composition of the first stream of text changes. Quantifying the content and nature of the first stream of text may begin by generating a baseline representation of the content of the first stream of text as represented by a first matrix. Once generated, the first matrix may be used as a control against subsequently received sequences of text. In this regard, a second matrix may be generated from a second sequence of text and compared to the first matrix to determine the differences between the first sequence of text and the second sequence of text. Once a difference is determined, the difference may be compared to a threshold value and, when the difference exceeds the threshold value, an administrator may be notified and corrective action taken.
    Type: Grant
    Filed: January 16, 2020
    Date of Patent: October 5, 2021
    Assignee: Capital One Services, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Publication number: 20210112095
    Abstract: A system including at least one processor; and at least one memory having stored thereon computer program code that, when executed by the at least one processor, controls the at least one processor to: receive an email addressed to a user; separate the email into a plurality of email components; analyze, using respective machine-learning techniques, each of the plurality of email components; feed the analysis of each of the plurality of email components into a stacked ensemble analyzer; and based on an output of the stacked ensemble analyzer, determine whether the email is malicious.
    Type: Application
    Filed: October 12, 2020
    Publication date: April 15, 2021
    Inventors: Christopher Bayan Bruss, Stephen Fletcher, Lei Yu, Jakob Kressel
  • Publication number: 20210019559
    Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.
    Type: Application
    Filed: April 7, 2020
    Publication date: January 21, 2021
    Applicant: Capital One Services, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Publication number: 20210019546
    Abstract: Methods and systems disclosed herein may quantify the content and nature of a first stream of text to detect when the typical composition of the first stream of text changes. Quantifying the content and nature of the first stream of text may begin by generating a baseline representation of the content of the first stream of text as represented by a first matrix. Once generated, the first matrix may be used as a control against subsequently received sequences of text. In this regard, a second matrix may be generated from a second sequence of text and compared to the first matrix to determine the differences between the first sequence of text and the second sequence of text. Once a difference is determined, the difference may be compared to a threshold value and, when the difference exceeds the threshold value, an administrator may be notified and corrective action taken.
    Type: Application
    Filed: January 16, 2020
    Publication date: January 21, 2021
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Patent number: 10805347
    Abstract: A system including at least one processor; and at least one memory having stored thereon computer program code that, when executed by the at least one processor, controls the at least one processor to: receive an email addressed to a user; separate the email into a plurality of email components; analyze, using respective machine-learning techniques, each of the plurality of email components; feed the analysis of each of the plurality of email components into a stacked ensemble analyzer; and based on an output of the stacked ensemble analyzer, determine whether the email is malicious.
    Type: Grant
    Filed: July 10, 2019
    Date of Patent: October 13, 2020
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Christopher Bayan Bruss, Stephen Fletcher, Lei Yu, Jakob Kressel
  • Patent number: 10657416
    Abstract: Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.
    Type: Grant
    Filed: July 17, 2019
    Date of Patent: May 19, 2020
    Assignee: Capital One Services, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Patent number: 10579894
    Abstract: Methods and systems disclosed herein may quantify the content and nature of a first stream of text to detect when the typical composition of the first stream of text changes. Quantifying the content and nature of the first stream of text may begin by generating a baseline representation of the content of the first stream of text as represented by a first matrix. Once generated, the first matrix may be used as a control against subsequently received sequences of text. In this regard, a second matrix may be generated from a second sequence of text and compared to the first matrix to determine the differences between the first sequence of text and the second sequence of text. Once a difference is determined, the difference may be compared to a threshold value and, when the difference exceeds the threshold value, an administrator may be notified and corrective action taken.
    Type: Grant
    Filed: July 17, 2019
    Date of Patent: March 3, 2020
    Assignee: Capital One Service, LLC
    Inventors: Keegan Hines, Christopher Bayan Bruss
  • Publication number: 20190349400
    Abstract: A system including at least one processor; and at least one memory having stored thereon computer program code that, when executed by the at least one processor, controls the at least one processor to: receive an email addressed to a user; separate the email into a plurality of email components; analyze, using respective machine-learning techniques, each of the plurality of email components; feed the analysis of each of the plurality of email components into a stacked ensemble analyzer; and based on an output of the stacked ensemble analyzer, determine whether the email is malicious.
    Type: Application
    Filed: July 10, 2019
    Publication date: November 14, 2019
    Inventors: Christopher Bayan Bruss, Stephen Fletcher, Lei Yu, Jakob Kressel
  • Patent number: 10397272
    Abstract: A system including at least one processor; and at least one memory having stored thereon computer program code that, when executed by the at least one processor, controls the at least one processor to: receive an email addressed to a user; separate the email into a plurality of email components; analyze, using respective machine-learning techniques, each of the plurality of email components; feed the analysis of each of the plurality of email components into a stacked ensemble analyzer; and based on an output of the stacked ensemble analyzer, determine whether the email is malicious.
    Type: Grant
    Filed: October 23, 2018
    Date of Patent: August 27, 2019
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Christopher Bayan Bruss, Stephen Fletcher, Lei Yu, Jakob Kressel
  • Patent number: 9361290
    Abstract: According to one aspect of the present invention, a system and methodology is provided which provides valuable risk assessment and warnings as well as predictions of possible events which may occur in corporate, governmental, business or other types of organizational settings. In a personal context, the present invention may provide valuable data regarding predicted personal behavior, events, activities as well as data regarding affinity or lack thereof between and among individuals as well as a great many other characteristics of inter-personal relationships.
    Type: Grant
    Filed: January 18, 2014
    Date of Patent: June 7, 2016
    Inventors: Christopher Bayan Bruss, Pouya Johnathon Ehsani
  • Publication number: 20150260531
    Abstract: A system and methodology that provides travel routes that minimize crash risk and add a safety factor to the determination of preferred routes of travel. Multiple elements of safety are considered in determining preferred routes of travel. This may include consideration of the user's physiological and/or psychological state during the time of travel. Alternatively or in addition, required driving maneuvers, roadway crash histories, demographic data and/or secondary task engagement while driving by the user may be considered in determining the optimal route of travel given the foregoing safety factors.
    Type: Application
    Filed: March 12, 2014
    Publication date: September 17, 2015
    Applicant: LOGAWI DATA ANALYTICS, LLC
    Inventors: Pouya Johnathon Ehsani, Christopher Bayan Bruss, Jian Khadem Khodadad
  • Publication number: 20150205787
    Abstract: According to one aspect of the present invention, a system and methodology is provided which provides valuable risk assessment and warnings as well as predictions of possible events which may occur in corporate, governmental, business or other types of organizational settings. In a personal context, the present invention may provide valuable data regarding predicted personal behavior, events, activities as well as data regarding affinity or lack thereof between and among individuals as well as a great many other characteristics of inter-personal relationships.
    Type: Application
    Filed: January 18, 2014
    Publication date: July 23, 2015
    Applicant: Logawi Data Analytics, LLC
    Inventors: Christopher Bayan Bruss, Pouya Johnathon Ehsani