题　目：Path-Based Fraud Detection, Algorithms, Systems and Impacts

嘉　宾：You Peng, Postdoctoral Researcher, The Chinese University of Hong Kong

主持人：林学民　讲席教授　上海交通大学安泰经济与管理学院

时　间：2022年2月21日（周一）13:30-15:00（腾讯会议）

（校内师生如需会议号和密码，请于2月20日12:00前发送电邮 dbi@acem.sjtu.edu.cn 获取）

内容简介:

With the rapid development of information technology, data generated by an increasing number of applications is being modeled as graphs. On one hand, the graph structure is able to encode complex relationships among entities. Examples include social networks, e-commerce transactions, and electronic payments, etc. It is typical for such graphs to contain hundreds of millions of edges and vertices. Sophisticated analytics over such large-scale graphs provides valuable insights to the underlying dataset and interactions among different entities. In many real-life applications, various path analysis is of great importance for a deeper understanding and better management of these networks. In this talk, we discuss several works about fraud detection by path-based patterns, including a new system GraphS, a theoretical result, and a FPGA-optimization. It is note that GraphS system is developed at Alibaba to actively monitor various on-line fraudulent activities based on cycle detection.

This talk is based on several projects with Jingren Zhou (Vice President at Alibaba Group).

演讲人简介：

Dr. Peng is currently a postdoctoral researcher in the Database Research Group at The Chinese University of Hong Kong. He obtained his Ph.D. from The University of New South Wales in 2020, and received his bachelor’s degree from Tsinghua University in 2016. His research interests lie in the areas of graph databases and efficient query algorithms.

欢迎广大师生参加!