报告题目: Dynamic Fraud Detection via Sequential Modeling
With the popularity of web services, security issues are calling our attention. Fake news on Facebook, vandalism on Wikipedia and frauds on Amazon retail, impose severe security threats to the legitimate participants. Nowadays, Machine learning (ML) technique offers an unprecedented opportunity to the aforementioned platforms for bad actor’s detection, whereas it also faces some new challenges. To share these open problems & potential solutions, this talk will be carried out with a focus in:
Unavailability of sufficient labeled data: traditional machine learning approaches usually require a balanced training dataset consisting of normal and abnormal samples. In practice, however, there are far fewer abnormal labeled samples than normal ones.
Lack of high-quality labels: the labeled training records often have the time gap between the time that fraudulent users commit fraudulent actions and the time that they are suspended by the platforms.
Time-evolving nature: users are always changing their behaviors over time.
郑盼盼，2020年毕业于美国阿肯色大学计算机科学与工程系，获工学博士学位。 现就职于美国亚马逊（云服务）人工智能实验室，担任应用科学家，从事人工智能技术在云服务安全方面的研究和落地工作，其主要研究领域是大规模数据流的异常点检测。曾在顶级人工智能和数据挖掘会议和期刊发表过多篇文章（如AAAI, CIKM, PKDD, PAKDD, Big Data, Neurocomputing 及DTRAP），2021年获得“亚马逊月最佳员工”称号（部门级别 2 / 70）。