Learning to Solve an Order Fulfillment Problem in Milliseconds with Edge-Feature-Embedded Graph Attention

no code implementations • 29 Sep 2021 • Jingwei Yang, Qingchun Hou, Xiaoqing Wang, Yang Wei, Yuming Deng, Hongyang Jia, Ning Zhang

Such a problem is computationally hard to address by exact mathematical programming methods.

Combinatorial Optimization Graph Attention +1

Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning: A Field Experiment

no code implementations • 5 Dec 2019 • Jiaxi Liu, Yidong Zhang, Xiaoqing Wang, Yuming Deng, Xingyu Wu

Field experiment results suggest that DRCR is a more appropriate reward function than revenue, which is widely used by current literature.

reinforcement-learning Reinforcement Learning (RL)

A Capsule Network for Recommendation and Explaining What You Like and Dislike

1 code implementation • 1 Jul 2019 • Chenliang Li, Cong Quan, Li Peng, Yunwei Qi, Yuming Deng, Libing Wu

A sentiment capsule architecture with a novel Routing by Bi-Agreement mechanism is proposed to identify the informative logic unit and the sentiment based representations in user-item level for rating prediction.

Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning

no code implementations • 27 Sep 2018 • Jiaxi Liu, Yidong Zhang, Xiaoqing Wang, Yuming Deng, Xingyu Wu, Miaolan Xie

We first extend the application of dynamic pricing to a continuous pricing action space.

reinforcement-learning Reinforcement Learning (RL)