LNA Lab: Industry Showcase

Graph Modelling and Analysis for e-Commerce

 

A simplified model of a graph/network represented by blue circles (fake buyers) and red circles (products to promote) joined by intersecting line

Simplified model of farm clicking detection. Image: Ying Zhang

Research Lead 
A/Prof Ying Zhang

Collaborators
Alibaba Group

Graph analytics provides powerful insights into how to unlock the value graphs hold. Due to their powerful capabilities, techniques for analysing graphs are becoming an increasingly popular topic of study in both academics and industry. As such, a host of researchers in the fields of e-commerce, cybersecurity, social networks, environmental issues, defence, and many more, are turning to graph modelling to support real-world data analysis.

In one of our recent collaboration projects with Alibaba Group, we provided solutions for large-scale graph analysis of various e-commerce graph data. One example is the real-time farm clicking detection technique, which was launched in the 2017 Double 11 shopping festival, and significantly increase the recall by 40%. By developing efficient and scalable biclique detection algorithms on large scale dynamic bipartite graph with billions of buyers and productions and 10+ billions of transactions, we can identify the potential fake buyers in a real-time manner.

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.