Summary of Semi-supervised Credit Card Fraud Detection Via Attribute-driven Graph Representation, by Sheng Xiang et al.
Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation
by Sheng Xiang, Mingzhi Zhu, Dawei Cheng, Enxia Li, Ruihui Zhao, Yi Ouyang, Ling Chen, Yefeng Zheng
First submitted to arxiv on: 24 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a semi-supervised graph neural network for credit card fraud detection, addressing the limitations of current methods that rely heavily on labeled transaction records. By leveraging unlabeled data, the approach constructs a temporal transaction graph and uses a Gated Temporal Attention Network (GTAN) to learn transaction representations. Risk propagation among transactions models fraud patterns. The method is tested on three datasets, outperforming state-of-the-art baselines. Even with only a small proportion of labeled data, the semi-supervised experiments demonstrate excellent fraud detection performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to solve a big problem: credit card fraud costs a lot for both users and banks. Right now, we use machine learning to find fake transactions by looking at labeled records. But these labeled records are rare, so we don’t really get to use the information from all the other transactions. To fix this, the researchers created a new way to look at credit card transactions using a special kind of computer network called a graph neural network. This lets us learn more about each transaction and find patterns that might be fake. They tested their method on some real data and it worked really well. |
Keywords
» Artificial intelligence » Attention » Graph neural network » Machine learning » Semi supervised
