Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Utilizing a time-dependent graph convolutional neural network for fraudulent transaction identification

Utilizing a time-dependent graph convolutional neural network for fraudulent transaction identification

US Patent 11403643 · Granted Aug 2, 2022

Estimated economic value: $170,999,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Time series of sketches for approximate query processing2025
Mask conditioned image transformation based on a text prompt2025
Determining user affinities for content generation applications2025
Quantifying and improving the performance of computation-based classifiers2025
Generating weighted contextual themes to guide unsupervised keyphrase relevance 2025
Determining user affinities for content generation applications2024
Machine learning models applied to interaction data for facilitating modificatio2023
Prototype-based machine learning reasoning interpretation2023
Determining feature impact within machine learning models using prototypes acros2023
Anomaly detection and reporting for machine learning models2022
Machine learning based on post-transaction data2022
Machine learning models applied to interaction data for facilitating modificatio2022