Capital One Services, LLC

Haytham Yaghi

Tania Cruz Morales

Shannon Yogerst

Purva Shanker

Joshua S Edwards

Tyler Maiman

Bryant Alan Yee

Samuel Rapowitz

Shabnam Kousha

Joshua Peters

Samuel Yip

Evelyn Burke

Caroline Williams

Maxwell Gotsch

Methods and systems for reducing network traffic between a service and client devices. In some aspects, the system receives a first data stream for a first type of communication between a service and a client device for a user. In response to determining that the first data stream includes an unresolved user query, the system determines that a second type of communication occurred between the service and the user. The system processes a second data stream for the second type of communication to determine that the second type of communication includes the unresolved user query and a service response to the unresolved user query. The system provides the unresolved user query and the service response to update a machine learning model used by the service to generate service responses to one or more user queries during a future communication of the first type.

Systems and methods for reducing network traffic

Systems and methods for labeling data for artificial neural network models when data is received as real-time data and batch-processed data are disclosed herein. The system may receive a first data stream. The system may generate a first vector representation of the first real-time processed data. The system may determine the first label for a first training datum. The system may determine whether all data used to generate a final label has been received. The system may assign a first label type to the first label.

Systems and methods for label generation for real-time processed and batch-processed streams for machine learning training

Disclosed embodiments may include a system for curating online vehicle reservations. The system may determine, from received vehicle data including first timing data and indicating a selected vehicle, that the selected vehicle is electric. The system may receive accommodation data including second timing data and indicating a selected accommodation. The system may determine, from comparing the first timing data to the second timing data, that the selected vehicle will likely require charging at the selected accommodation. The system may determine whether the accommodation data includes an indication of electric vehicle charging facilities. Responsive to determining that the selected accommodation does not provide the indication of electric vehicle charging facilities, the system may generate a first graphical user interface warning that no charging station is available for the selected vehicle at the selected accommodation and transmit the first graphical user interface to a user device for display.

Systems and methods for curating online vehicle reservations to avoid electric vehicle battery depletion

Disclosed herein are system, method, and computer program product embodiments for training and deploying a machine learning model to generate an assessment of risks and mitigations in response to a novel initiative request. After generating labeled data from a corpus of prior risk assessments, a machine learning model may be trained to programmatically generate a risk assessment in response to a novel initiative request. A risk auditor may subsequently review the risk assessment generated using the machine learning model to provide various feedback reflecting the accuracy of the risks and mitigations. The machine learning model may then be retrained based on the feedback provided by the risk auditor to provide more accurate risks and mitigations in response to future initiatives.

Method for scoring confidence of an algorithmically proposed risk

Growing community of inventors

Oakton, VA, United States of America

Haytham Yaghi