Patents by Inventor Lewis Jordan
Lewis Jordan 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).
-
Patent number: 11900294Abstract: Systems and methods for automated path-based recommendation for risk mitigation are provided. An entity assessment server, responsive to a request for a recommendation for modifying a current risk assessment score of an entity to a target nsk assessment score, accesses an input attribute vector for the entity and clusters of entities defined by historical attribute vectors. The entity assessment server assigns the input attribute vector to a particular cluster and determines a requirement on movement from a first point to a second point in a multi-dimensional space based on the statistics computed from the particular cluster. The first point corresponds to the current risk assessment score and the second point corresponds to the target risk assessment score. The entity assessment server computes an attribute-change vector so that a path defined by the attribute-change vector complies with the requirement and generates the recommendation from the attribute-change vector.Type: GrantFiled: August 19, 2020Date of Patent: February 13, 2024Assignee: EQUIFAX INC.Inventors: Stephen Miller, Lewis Jordan, Matthew Turner, Mark Day, Allan Joshua
-
Patent number: 11868891Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: GrantFiled: August 31, 2022Date of Patent: January 9, 2024Assignee: Equifax Inc.Inventors: Matthew Turner, Lewis Jordan, Allan Joshua
-
Publication number: 20230111785Abstract: Certain aspects involve an automated recommendation for risk mitigation. An entity assessment server, responsive to a request for a recommendation for achieving a target status of a risk indicator, accesses a set of input attributes for the entity and obtains a quantity of available resource useable for modifying at least resource-dependent attribute values of the entity. The entity assessment server generates a resource allocation plan for the available resource according to a first risk assessment model and updates the set of input attribute values based on the resource allocation plan. The entity assessment server further determines an updated value of the risk indicator for the entity based on the updated set of input attribute values according to a second risk assessment model and generates the recommendation to include the resource allocation plan of the available resource if the updated value of the risk indicator achieves the target status.Type: ApplicationFiled: February 22, 2021Publication date: April 13, 2023Inventors: Allan JOSHUA, Stephen MILLER, Matthew TURNER, Lewis JORDAN
-
Publication number: 20220414469Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: ApplicationFiled: August 31, 2022Publication date: December 29, 2022Inventors: Matthew TURNER, Lewis JORDAN, Allan JOSHUA
-
Publication number: 20220335348Abstract: Systems and methods for automated path-based recommendation for risk mitigation are provided. An entity assessment server, responsive to a request for a recommendation for modifying a current risk assessment score of an entity to a target nsk assessment score, accesses an input attribute veclor for the entity and clusters of entities defined by historical attribute vectors. The entity assessment server assigns the input attribute vector to a particular cluster and determines a requirement on movement from a first point to a second point in a multi-dimensional space based on tire statistics computed from tltc particular cluster The first point corresponds to tire current risk assessment score and the second point corresponds to the target nsk assessment score. The entity assessment server computes an attribute-changc vecior so that a path defined by the attribute-change vector complies with the requirement and generates tlic recommendation from the attribute-changc vector.Type: ApplicationFiled: August 19, 2020Publication date: October 20, 2022Inventors: Stephen MILLER, Lewis JORDAN, Matthew TURNER, Mark DAY, Allan JOSHUA
-
Patent number: 11468315Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: GrantFiled: October 24, 2018Date of Patent: October 11, 2022Assignee: EQUIFAX INC.Inventors: Matthew Turner, Lewis Jordan, Allan Joshua
-
Patent number: 11049019Abstract: Certain embodiments involve generating or optimizing a neural network for generating analytical or predictive outputs. The neural network can be generated using a relationship between various predictor variables and an outcome (e.g., a condition's presence or absence). The neural network can be used to determine a relationship between each of the predictor variables and a response variable. The neural network can be optimized by iteratively adjusting the neural network such that a monotonic relationship exists between each of the predictor variables and the response variable. The optimized neural network can be used both for accurately determining response variables using predictor variables and determining adverse action codes for the predictor variables, which indicate an effect or an amount of impact that a given predictor variable has on the response variable.Type: GrantFiled: October 4, 2017Date of Patent: June 29, 2021Assignee: EQUIFAX INC.Inventors: Lewis Jordan, Matthew Turner, Michael McBurnett
-
Publication number: 20210182690Abstract: Certain embodiments involve generating or optimizing a neural network for generating analytical or predictive outputs. The neural network can be generated using a relationship between various predictor variables and an outcome (e.g., a condition's presence or absence). The neural network can be used to determine a relationship between each of the predictor variables and a response variable. The neural network can be optimized by iteratively adjusting the neural network such that a monotonic relationship exists between each of the predictor variables and the response variable. The optimized neural network can be used both for accurately determining response variables using predictor variables and determining adverse action codes for the predictor variables, which indicate an effect or an amount of impact that a given predictor variable has on the response variable.Type: ApplicationFiled: March 2, 2021Publication date: June 17, 2021Inventors: Lewis JORDAN, Matthew TURNER, Michael MCBURNETT
-
Publication number: 20210174264Abstract: Certain aspects involve training tree-based machine-learning models for computing predicted responses and generating explanatory data for the models. For example, independent variables having relationships with a response variable are identified. Each independent variable corresponds to an action or observation for an entity. The response variable has outcome values associated with the entity. Splitting rules are used to generate the tree-based model, which includes decision trees for determining relationships between independent variables and a predicted response associated with the response variable. The tree-based model is iteratively adjusted to enforce monotonicity with respect to representative response values of the terminal nodes. For instance, one or more decision trees are adjusted such that one or more representative response values are modified and a monotonic relationship exists between each independent variable and the response variable.Type: ApplicationFiled: February 22, 2021Publication date: June 10, 2021Inventors: Lewis JORDAN, Matthew TURNER, Finto ANTONY
-
Patent number: 11010669Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: GrantFiled: September 8, 2020Date of Patent: May 18, 2021Assignee: EQUIFAX INC.Inventors: Matthew Turner, Lewis Jordan, Allan Joshua
-
Patent number: 10963817Abstract: Certain aspects involve training tree-based machine-learning models for computing predicted responses and generating explanatory data for the models. For example, independent variables having relationships with a response variable are identified. Each independent variable corresponds to an action or observation for an entity. The response variable has outcome values associated with the entity. Splitting rules are used to generate the tree-based model, which includes decision trees for determining relationships between independent variables and a predicted response associated with the response variable. The tree-based model is iteratively adjusted to enforce monotonicity with respect to representative response values of the terminal nodes. For instance, one or more decision trees are adjusted such that one or more representative response values are modified and a monotonic relationship exists between each independent variable and the response variable.Type: GrantFiled: October 30, 2017Date of Patent: March 30, 2021Assignee: EQUIFAX INC.Inventors: Lewis Jordan, Matthew Turner, Finto Antony
-
Publication number: 20200401894Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: ApplicationFiled: September 8, 2020Publication date: December 24, 2020Inventors: Matthew TURNER, Lewis JORDAN, Allan JOSHUA
-
Publication number: 20200387832Abstract: Certain aspects involve training tree-based machine-learning models for computing predicted responses and generating explanatory data for the models. For example, independent variables having relationships with a response variable are identified. Each independent variable corresponds to an action or observation for an entity. The response variable has outcome values associated with the entity. Splitting rules are used to generate the tree-based model, which includes decision trees for determining relationships between independent variables and a predicted response associated with the response variable. The tree-based model is iteratively adjusted to enforce monotonicity with respect to representative response values of the terminal nodes. For instance, one or more decision trees are adjusted such that one or more representative response values are modified and a monotonic relationship exists between each independent variable and the response variable.Type: ApplicationFiled: October 30, 2017Publication date: December 10, 2020Inventors: Lewis JORDAN, Matthew TURNER, Finto ANTONY
-
Publication number: 20200134439Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: ApplicationFiled: October 24, 2018Publication date: April 30, 2020Inventors: Matthew Turner, Lewis Jordan, Allan Joshua
-
Patent number: 10558913Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: GrantFiled: October 29, 2018Date of Patent: February 11, 2020Assignee: EQUIFAX INC.Inventors: Matthew Turner, Lewis Jordan, Allan Joshua
-
Publication number: 20180025273Abstract: Certain embodiments involve generating or optimizing a neural network for generating analytical or predictive outputs. The neural network can be generated using a relationship between various predictor variables and an outcome (e.g., a condition's presence or absence). The neural network can be used to determine a relationship between each of the predictor variables and a response variable. The neural network can be optimized by iteratively adjusting the neural network such that a monotonic relationship exists between each of the predictor variables and the response variable. The optimized neural network can be used both for accurately determining response variables using predictor variables and determining adverse action codes for the predictor variables, which indicate an effect or an amount of impact that a given predictor variable has on the response variable.Type: ApplicationFiled: October 4, 2017Publication date: January 25, 2018Inventors: Lewis Jordan, Matthew Turner, Michael McBurnett
-
Patent number: 6212115Abstract: A test system for SRAM uses two mechanical probes to contact the bit lines of a column of SRAM storage cells. A word line is selected and a voltage is applied through the first mechanical probe to the first bit line forcing the second and complementary bit line to have a conducting FET coupled via contacts and a section of the second bit line to the second mechanical probe. A variable voltage is applied to the second mechanical probe and the corresponding resulting currents are measured. The first and second mechanical probes are then reversed and the process repeated. The voltage versus current from the second mechanical probe determines electrical characteristics of the contacts of the SRAM bit cell. The resulting data determining the electrical characteristics of the SRAM contacts are used to control process parameters during manufacture, set process parameters during manufacturing development, and to aid in failure analysis of manufactured SRAM bit cells.Type: GrantFiled: July 19, 2000Date of Patent: April 3, 2001Assignee: Advanced Micro Devices, Inc.Inventor: Lewis Jordan