Gan Luan

Title: Gan Luan: Reinforcement Learning for Online Retail

Introduction

Gan Luan is an inventor associated with Chicago, Illinois, and Amazon Technologies, Inc. His patent work addresses the use of machine learning to evaluate how page-view contexts affect users in an online retail system.

Latest Patents

Luan is named on 1 patent: “Enhanced reinforcement learning-based uplift modeling to mitigate discrepancies.” The invention describes identifying the context of a product page view and using a trained neural network to estimate the difference in outcomes between users who see that context and users who do not. Based on the estimated uplift, the system can take an action intended to mitigate the effects of the page-view context.

Career Highlights

Luan’s listed patent reflects work at the intersection of reinforcement learning, uplift modeling, and online retail. It focuses on using estimated differences between user groups to inform system actions.

Collaborations

The provided information lists Yingchuan Li and Hansu Gu as Luan’s coworkers. Their specific roles in the patent or related work are not specified.

Conclusion

Gan Luan’s patent contribution centers on applying reinforcement learning-based uplift modeling to help online retail systems assess and respond to page-view contexts.