Zhichao Han

Zhichao Han

Auto-generated profile, based on publicly available information

Zhichao Han


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 March 2025
Verified
Book Chapter
Open access
PDF file
SRSusie Xi Rao
Susie Xi Rao
JJJiawei Jiang
Jiawei Jiang
ZHZhichao Han
Zhichao Han
HYHang Yin
Hang Yin
We provide a systematic review of the endeavors of e-commerce companies in combating transaction risks that involve buyers, sellers, items, and transactions. There has been a paradigm shift from rule-based systems to simple machine learning-based systems to deep learning-based systems. This transformation has also involved multimodal data engineering efforts like rule extraction, feature engineering on text and image, graph-structured abstraction, etc. In this review, we not only reflect on the shifts in data and systems but also the role of human experts, as well as the infrastructure support for such shifts, which are oftentimes neglected in previous review articles. The key conclusions from this review are three. First, there has been an increasing focus on multimodal data engineering efforts, explainability, and human-in-the-loop systems. Second, despite certain contributions to the online scalability of fraud detection systems, this topic has remained understudied. Third, newer research trends are on federated learning and adversarial machine learning, reinforcement learning, large language models, and their applicability and feasibility to integrate into the existing e-commerce fraud detection systems.