Mengting Gu

Title: Innovations by Mengting Gu

Introduction

Mengting Gu is an accomplished inventor based in Stanford, California. She has made significant contributions to the field of machine learning and data analysis, holding two patents that showcase her innovative approach to technology.

Latest Patents

Her latest patents include a system, method, and computer program product for dynamic node classification in temporal-based machine learning classification models. This invention describes a method that involves receiving graph data of a discrete time dynamic graph, converting it to a time-augmented spatio-temporal graph, and generating an adjacency matrix based on a temporal walk. The method also includes generating an adaptive information transition matrix and determining feature vectors based on nodes and their attributes. This innovative approach allows for effective classification of nodes in dynamic graphs.

Another notable patent is a system for analyzing multivariate time series using a convolutional Fourier network. This system is designed to receive a time series of historical data points and generate a machine learning model that predicts a contemporary target transaction metric. The model is configured to provide outputs that are essential for understanding contemporary transaction metrics based on historical data.

Career Highlights

Mengting Gu is currently employed at Visa International Service Association, where she applies her expertise in machine learning and data analysis. Her work at Visa has allowed her to contribute to advancements in financial technology and data processing.

Collaborations

She has collaborated with notable colleagues, including Michael Yeh and Liang Wang, further enhancing her innovative projects and research.

Conclusion

Mengting Gu's contributions to the fields of machine learning and data analysis are significant, as evidenced by her patents and work at Visa. Her innovative spirit continues to drive advancements in technology and data processing.