Yingchuan Li

Title: Yingchuan Li and Reinforcement Learning-Based Uplift Modeling

Introduction

Yingchuan Li is an inventor based in Bellevue, Washington, and is associated with Amazon Technologies, Inc. His patent work addresses the use of reinforcement learning and uplift modeling in online retail systems. The available information identifies 1 patent associated with him.

Latest Patents

Li’s patent, “Enhanced Reinforcement Learning-Based Uplift Modeling to Mitigate Discrepancies,” describes devices, systems, and methods for assessing the context of a product page view. The method uses a neural network to estimate the difference in outcomes between users who are presented with a particular page-view context and users who are not. A trained neural network determines the uplift, which can then inform an action intended to mitigate that context.

Career Highlights

The patent reflects work at the intersection of machine learning, online retail, and user experience. Its approach uses estimated differences between user groups to guide decisions about how product information is presented.

Collaborations

Hansu Gu and Gan Luan are identified as Li’s coworkers. The available information does not specify their roles in the patent or the extent of their collaboration.

Conclusion

Yingchuan Li’s identified patent applies reinforcement learning-based uplift modeling to online retail page views, highlighting a data-driven approach to improving how product contexts are managed.