School of
Information Technology and Electrical Engineering

Speaker: Ms Shijie Zhang
Seminar Date: Fri, 11/10/2019 - 14:00
Venue: 78-631; Data Science MM Lab
Host: Dr Hongzhi Yin

Seminar Type:  PhD Confirmation Seminar


On E-commerce platforms, understanding the relationships (e.g., substitute and complement) among products from user's explicit feedback, such as users' online transactions, is of great importance to optimize customer engagement life cycle. However, the significance of such relationships is usually neglected by existing recommender systems. Current research in product relationship inference extract the textual features of products from the whole reviews and descriptions which requires large memory spaces for learned features, making these models inefficient on large datasets. In addition, they only consider the review texts, and the valuable information within users' historical purchase behaviours is neglected. More importantly, it is impractical to assume the constant availability of high-quality and sufficient reviews, which are common in user reviews. 

We propose a semi-supervised deep embedding model, namely, Substitute Products Embedding Model (SPEM), which models the substitutable relationship between products by preserving the second-order proximity, negative first-order proximity and semantic similarity in a product co-purchasing graph based on user's purchasing behaviours. With SPEM, the learned representations of two substitutable products align closely in the latent embedding space. 


Shijie is a PhD candidate at DKE group under supervision of Dr. Hongzhi Yin and A/Prof Helen Huang. She received her master degree in Information Technology from the University of Queensland and bachelor degree in Information and Computing Science from the Shandong University, respectively. Her research interest includes recommender systems, network embedding and deep learning.