Xi Kan

Title: Innovations of Xi Kan

Introduction

Xi Kan is an accomplished inventor based in Austin, TX, known for his contributions to the field of machine learning. He has been awarded 2 patents that focus on enhancing multitask learning models and interpreting black box models in financial transactions. His work is pivotal in advancing the capabilities of machine learning applications.

Latest Patents

One of Xi Kan's latest patents is titled "System, method, and computer program product for generating and improving multitask learning models." This invention provides systems, methods, and computer program products designed to generate and enhance multitask learning models. The method involves determining accuracy metrics based on multiple machine learning models performing various tasks and optimizing the number of shared layers in the multitask learning model.

Another significant patent is "System, method, and computer program product for interpreting black box models by perturbing transaction parameters." This computer-implemented method focuses on analyzing payment transactions by perturbing transaction parameters to generate perturbed risk scores. It identifies impact parameters that influence risk scores, thereby improving the interpretability of machine learning models in financial contexts.

Career Highlights

Xi Kan is currently employed at Visa International Service Association, where he applies his expertise in machine learning to develop innovative solutions for financial transactions. His work at Visa has positioned him as a key player in the intersection of technology and finance.

Collaborations

Xi Kan collaborates with talented individuals in his field, including Dan Wang and Sheng Wang. These collaborations enhance the innovative potential of their projects and contribute to the advancement of machine learning technologies.

Conclusion

Xi Kan's contributions to machine learning through his patents and work at Visa International Service Association highlight his role as a significant innovator in the field. His inventions are paving the way for more efficient and interpretable machine learning applications.