Patents by Inventor Benjamin Wellmann
Benjamin Wellmann 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: 20250225584Abstract: Systems and methods for optimizing the combination of products and services a business offers to customers, identifying a combination of top markets a business offers to customers for growth opportunities, and optimizing advertisements. In one implementation, the disclosed system includes at least one processing device and at least one non-transitory memory containing software code configured to cause the processing device to: gather customer data and financial institution data from a plurality of data sources; extract a plurality of customer behavior features and a plurality of financial institution behavior features; process the customer behavior features and financial institution behavior features using one or more trained foundation models; input the foundation model outputs and a plurality of goal inputs into a trained product model; and output a natural-language product response.Type: ApplicationFiled: February 27, 2024Publication date: July 10, 2025Applicant: FIDELITY INFORMATION SERVICES, LLCInventors: Benjamin WELLMANN, Amit AGGARWAL, Lance Charles TAPPA, Vivek Ravi KUMAR
-
Publication number: 20250225546Abstract: Systems and methods for optimizing the combination of products and services a business offers to customers, identifying a combination of top markets a business offers to customers for growth opportunities, and optimizing advertisements. In one implementation, the disclosed system includes at least one processing device and at least one non-transitory memory containing software code configured to cause the processing device to: gather customer data and financial institution data from a plurality of data sources; extract a plurality of customer behavior features and a plurality of financial institution behavior features; process the customer behavior features and financial institution behavior features using one or more trained foundation models; input the foundation model outputs and a plurality of goal inputs into a trained product model; and output a natural-language advertisement response.Type: ApplicationFiled: February 27, 2024Publication date: July 10, 2025Applicant: FIDELITY INFORMATION SERVICES, LLCInventors: Benjamin WELLMANN, Amit AGGARWAL, Lance Charles TAPPA, Vivek Ravi KUMAR
-
Publication number: 20250225466Abstract: Systems and methods for optimizing the combination of products and services a business offers to customers, identifying a combination of top markets a business offers to customers for growth opportunities, and optimizing advertisements. In one implementation, the disclosed system includes at least one processing device and at least one non-transitory memory containing software code configured to cause the processing device to: gather customer data and financial institution data from a plurality of data sources; extract a plurality of customer behavior features and a plurality of financial institution behavior features; process the customer behavior features and financial institution behavior features using one or more trained foundation models; input the foundation model outputs and a plurality of goal inputs into a trained product model; and output a natural-language market response.Type: ApplicationFiled: February 27, 2024Publication date: July 10, 2025Applicant: FIDELITY INFORMATION SERVICES, LLCInventors: Benjamin WELLMANN, Amit AGGARWAL, Lance Charles TAPPA, Vivek Ravi KUMAR
-
Publication number: 20240221009Abstract: Systems and methods for developing temporal behavioral profiles are disclosed.Type: ApplicationFiled: December 30, 2022Publication date: July 4, 2024Applicant: Fidelity Information Services, LLCInventors: Benjamin Wellmann, Luke Jurat, Edward S. Barker, Stephane Wyper
-
Publication number: 20240220822Abstract: Systems and methods for predicting item group composition are disclosed. A system for predicting item group composition may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: receiving entity identification information and a timestamp associated with a transaction without receiving information distinguishing items associated with the transaction; determining, based on the entity identification information, a localized machine learning model trained to predict categories of items based on transaction information applying to all of the items associated with the transaction; and applying the localized machine learning model to a model input to generate predicted categories of items associated with the transaction, the model input including the received entity identification information and a timestamp but not including information distinguishing items associated with the transaction.Type: ApplicationFiled: December 29, 2022Publication date: July 4, 2024Applicant: Fidelity Information Services, LLCInventors: Benjamin Wellmann, Luke Jurat, Edward S. Barker, Stephane Wyper
-
Publication number: 20240045671Abstract: A method for training and using a machine-learning based model to reduce and troubleshoot incidents in a system may include receiving first metadata regarding a previous modification, extracting a first feature from the received first metadata, receiving second metadata regarding a previous incident, extracting a second feature from the received second metadata, training the machine-learning based model to learn an association between the previous modification and the previous incident, based on the extracted first feature and the extracted second feature, and using the machine-learning based model to determine a risk level for a proposed modification to a system.Type: ApplicationFiled: October 10, 2023Publication date: February 8, 2024Inventors: Per KARLSSON, Benjamin WELLMANN, Sheel SAKET, Vida LASHKARI
-
Patent number: 11842391Abstract: Systems and methods for activity risk management are disclosed. A system for activity risk management may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: accessing document data associated with at least one of a transaction or an individual; normalizing the document data; classifying the normalized document data; extracting model input data from the classified document data; applying a machine learning model to the extracted model input data to score the document data, the machine learning model having been trained to generate a favorability output indicating a favorability of the transaction or individual; and generating analysis data based on the scored document data.Type: GrantFiled: April 16, 2021Date of Patent: December 12, 2023Assignee: Fidelity Information Services, LLCInventors: Benjamin Wellmann, Zachary Jasinski, Matthew Petersen, Eric Bond, Daniel Wakeman, David Berglund
-
Patent number: 11816476Abstract: A method for training and using a machine-learning based model to reduce and troubleshoot incidents in a system may include receiving first metadata regarding a previous modification, extracting a first feature from the received first metadata, receiving second metadata regarding a previous incident, extracting a second feature from the received second metadata, training the machine-learning based model to learn an association between the previous modification and the previous incident, based on the extracted first feature and the extracted second feature, and using the machine-learning based model to determine a risk level for a proposed modification to a system.Type: GrantFiled: September 23, 2021Date of Patent: November 14, 2023Assignee: Fidelity Information Services, LLCInventors: Per Karlsson, Benjamin Wellmann, Sheel Saket, Vida Lashkari
-
Publication number: 20230342685Abstract: Some aspects of the present disclosure are directed to computer-implemented systems and methods for efficient ticket resolution. The methods may include: receiving a request to resolve an issue; analyzing, via natural language processing, the language in the request to determine the issue to be resolved; determining whether the issue meets a condition for automated resolution; if the condition is met: extracting, via an application programming interface and from the at least one user device, information needed to resolve the issue; and resolving the issue using the extracted information; and if the condition is not met: generating a ticket; assigning a work group to the ticket; determining whether a job aid associated with the issue exists; and forwarding at least one of: the job aid; received communications from the work group; and an estimated amount of time to resolution.Type: ApplicationFiled: June 28, 2023Publication date: October 26, 2023Applicant: FIDELITY INFORMATION SERVICES, LLCInventors: Joel E. DAKE, Damyn L. GESSLER, Shane M. PATZLSBERGER, Shane W. Strunk, Benjamin Wellmann
-
Publication number: 20230281541Abstract: Systems, devices, methods, and computer readable media for providing regulatory insight analysis are disclosed. In one implementation, the disclosed system may receive input data from a plurality of sources. Consistent with disclosed embodiments, the system may normalize the received input data. Further, the system may analyze the normalized input data, the analyzing comprising using logic for generating an output based on a first input including the normalized input data, a second input including calculation attributes, and a third input including one or more rules. The system may further be configured to store the output, continuously monitor the output as the output is stored, and generate one or more reports based on the stored output. Further, the system may receive, from a user and via a user interface, additional input data, a request to view the one or more generated reports, or a request for an additional output.Type: ApplicationFiled: March 3, 2023Publication date: September 7, 2023Applicant: Fidelity Information Services, LLCInventors: Benjamin Wellmann, Harry M. Stahl, David Berglund, Gary Michael Duma, John J. Cicinelli, Ravi Dangeti
-
Patent number: 11727331Abstract: Some aspects of the present disclosure are directed to computer-implemented systems and methods for efficient ticket resolution. The methods may include: receiving a request to resolve an issue; analyzing, via natural language processing, the language in the request to determine the issue to be resolved; determining whether the issue meets a condition for automated resolution; if the condition is met: extracting, via an application programming interface and from the at least one user device, information needed to resolve the issue; and resolving the issue using the extracted information; and if the condition is not met: generating a ticket; assigning a work group to the ticket; determining whether a job aid associated with the issue exists; and forwarding at least one of: the job aid; received communications from the work group; and an estimated amount of time to resolution.Type: GrantFiled: January 4, 2021Date of Patent: August 15, 2023Assignee: Fidelity Information Services, LLCInventors: Joel E. Dake, Damyn L. Gessler, Shane M Patzlsberger, Shane W. Strunk, Benjamin Wellmann
-
Publication number: 20230252561Abstract: A computer-implemented method for transaction settlement prediction may include receiving data for a plurality of past financial trades, training a machine learning model using the data for the plurality of past financial trades, receiving one or more parameters for a subject financial trade among a plurality of recently executed financial trades, determining a likelihood that the subject financial trade will fail using the trained machine learning model, determining a most likely reason that the subject financial trade will fail using the trained machine learning model, and presenting the likelihood that the subject financial trade will fail and the most likely reason that the subject financial trade will fail to a user.Type: ApplicationFiled: September 26, 2022Publication date: August 10, 2023Inventors: Benjamin WELLMANN, Mayur SHIRADHONKAR
-
Publication number: 20230206058Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing sequences of multi-modal entity data using convolutional neural networks. One of the methods includes receiving an input sequence of multi-modal feature vectors characterizing an entity over a time window, wherein each multi-modal feature vector in the input sequence corresponds to a different time interval during the time window; processing the input sequence of multi-modal feature vectors using a convolutional neural network to generate a latent sequence that comprises a plurality of latent feature vectors; processing the latent sequence of latent feature vectors using an aggregation neural network to generate an aggregated feature vector; and processing the aggregated feature vector using an output neural network to generate a prediction that characterizes the entity after the time window.Type: ApplicationFiled: December 29, 2021Publication date: June 29, 2023Inventors: Benjamin Wellmann, Gary Duma
-
Publication number: 20230196248Abstract: A method for improving the quality of a machine-learning based model includes generating a first query requesting a description of a change proposed to a system and an intended outcome of the change proposed; receiving a first response; generating a second query providing a risk of an incident associated with the change proposed and requesting justification of the change proposed in view of the risk; receiving a second response; generating a third query requesting an implementation plan for the change proposed; receiving a third response; generating an alert to an incident owner providing the description, intended outcome, risk, justification, and implementation plan of the change proposed; receiving a risk confirmation or rejection from the incident owner confirming or rejecting a relationship between the change proposed and the risk; and updating the machine-learning based model to learn an association between extracted features of the change and extracted features of the incident.Type: ApplicationFiled: December 22, 2021Publication date: June 22, 2023Inventors: Benjamin WELLMANN, Gary DUMA, Geoffrey Allan SPARKE, Brandon A. CASTRO
-
Patent number: 11645712Abstract: Systems and methods for entity risk management are disclosed. A system for entity risk management may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: establishing a connection between the system and a data source, the data source being remote from the system and associated with a first entity; receiving first document data from the data source; normalizing the first document data; classifying the normalized document data; extracting model input data from the classified document data; applying a machine learning model trained to predict risk levels using second document data to the extracted model input data to predict a risk level associated with the first entity; generating analysis data based on the predicted risk level; and based on the analysis data, transmitting an alert to a management device communicably connected to the system.Type: GrantFiled: April 16, 2021Date of Patent: May 9, 2023Assignee: Fidelity Information Services, LLCInventors: Benjamin Wellmann, Zachary Jasinski, Matthew Petersen, Eric Bond, Daniel Wakeman, David Berglund
-
Publication number: 20230135192Abstract: Systems and methods for activity risk management are disclosed. A system for activity risk management may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: classifying document data by identifying at least one marker in the document data, the at least one marker being associated with a document type; selecting an extraction model based on the document type; extracting model input data from the classified document data using the extraction model; applying a machine learning model to the extracted model input data to score the document data, the machine learning model having been trained with document data of a same document type as the document type associated with the at least one marker; and generating, based on the applying, a favorability output based on an amount of risk associated with the document data.Type: ApplicationFiled: December 29, 2022Publication date: May 4, 2023Inventors: Benjamin Wellmann, Zachary Jasinski, Matthew Petersen, Eric Bond, Daniel Wakeman, David Berglund
-
Publication number: 20230092819Abstract: A method for training and using a machine-learning based model to reduce and troubleshoot incidents in a system may include receiving first metadata regarding a previous modification, extracting a first feature from the received first metadata, receiving second metadata regarding a previous incident, extracting a second feature from the received second metadata, training the machine-learning based model to learn an association between the previous modification and the previous incident, based on the extracted first feature and the extracted second feature, and using the machine-learning based model to determine a modification to a system causing a change in a performance of the system.Type: ApplicationFiled: September 23, 2021Publication date: March 23, 2023Applicant: Fidelity Information Services, LLCInventors: Per KARLSSON, Benjamin WELLMANN, Sheel SAKET, Vida LASHKARI
-
Publication number: 20230091520Abstract: A method for training and using a machine-learning based model to reduce and troubleshoot incidents in a system may include receiving first metadata regarding a previous modification, extracting a first feature from the received first metadata, receiving second metadata regarding a previous incident, extracting a second feature from the received second metadata, training the machine-learning based model to learn an association between the previous modification and the previous incident, based on the extracted first feature and the extracted second feature, and using the machine-learning based model to determine a risk level for a proposed modification to a system.Type: ApplicationFiled: September 23, 2021Publication date: March 23, 2023Inventors: Per KARLSSON, Benjamin WELLMANN, Sheel SAKET, Vida LASHKARI
-
Publication number: 20220335517Abstract: Systems and methods for activity risk management are disclosed. A system for activity risk management may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: accessing document data associated with at least one of a transaction or an individual; normalizing the document data; classifying the normalized document data; extracting model input data from the classified document data; applying a machine learning model to the extracted model input data to score the document data, the machine learning model having been trained to generate a favorability output indicating a favorability of the transaction or individual; and generating analysis data based on the scored document data.Type: ApplicationFiled: April 16, 2021Publication date: October 20, 2022Inventors: Benjamin Wellmann, Zachary Jasinski, Matthew Petersen, Eric Bond, Daniel Wakeman, David Berglund
-
Publication number: 20220335518Abstract: Systems and methods for providing selective access to model output data are disclosed. A system for providing selective access to model output data may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: receiving, through an application programming interface (API) and from a requestor device, an API request for data, the API request identifying a requestor entity associated with the requestor device; determining a data type based on the API request; determining an authorization level of the requestor; accessing first model output data corresponding to the data type and the authorization level, the first model output data having been generated by a machine learning model trained to predict a risk level based on document data; and transmitting the first model output data to the requestor device.Type: ApplicationFiled: April 16, 2021Publication date: October 20, 2022Inventors: Benjamin Wellmann, Zachary Jasinski, Matthew Petersen, Eric Bond, Daniel Wakeman, David Berglund