How to implement a graph neural network for fraud detection from these papers?

Start by identifying papers with code links, such as CARE-GNN (2020) or DGFraud tools, and refer to their repositories for implementations. Then, adapt the methods to your dataset, but note that the repository lacks step-by-step tutorials, so additional resources may be needed.

What are the best papers for credit card fraud detection in this list?

Look for papers from recent years like AAAI 2023 on semi-supervised credit card fraud or KDD 2024 on cost-efficient fraud optimization. Filter by domain and method in the structured listings to find relevant works, but remember that quality isn't rated, so you'll need to evaluate based on citations and your needs.

Awesome fraud detection papers vs other paper lists like awesome-machine-learning?

This list is specialized for fraud detection with curated conference papers and direct links, whereas broader lists like awesome-machine-learning cover general topics without domain focus. It's better for in-depth fraud research but less versatile for other ML areas.

Are the papers in awesome fraud detection papers free to access?

Not all—many links point to conference proceedings or journals that may require paid access or institutional subscriptions. Some papers have arXiv preprints, but users without academic credentials might face barriers, as noted in the repository's reliance on official sources.

How to contribute or add a paper to this repository?

Submit a pull request on GitHub following the existing format, as encouraged by the 'PRs Welcome' badge. Ensure the paper is from a listed conference and include direct links to PDFs and code, but be aware that the maintainer's curation might not include all relevant works.

What's the difference between graph-based and traditional methods in fraud detection here?

The repository highlights papers using graph neural networks for relational data (e.g., financial networks) vs. traditional methods like ensemble learning. Browse sections by year or conference to compare techniques, but note that explanations are minimal, so prior knowledge is helpful.

Open-Awesome

Awesome Fraud Detection Research Papers

CC0-1.0Pythonv_0006

A curated collection of academic papers on data mining and machine learning techniques for fraud detection across various domains.

GitHub

1.8k stars330 forks0 contributors

What is Awesome Fraud Detection Research Papers?

Awesome Fraud Detection Papers is a curated list of academic research papers on data mining and machine learning techniques for detecting fraud. It compiles publications from major conferences like KDD, AAAI, and WWW, covering domains such as financial transactions, insurance claims, online reviews, and social networks. The repository helps researchers and engineers stay updated on advanced methods like graph neural networks, anomaly detection, and federated learning applied to fraud prevention.

Target Audience

Data scientists, machine learning researchers, and engineers working on fraud detection systems in industries like finance, e-commerce, cybersecurity, and insurance. It is also valuable for academics and students studying anomaly detection, graph mining, or applied AI.

Value Proposition

It saves significant time in literature review by providing a centralized, structured, and up-to-date collection of papers with direct links. Unlike generic academic search engines, it is domain-focused, includes code implementations when available, and connects to related curated lists for broader learning.

Overview

A curated list of data mining papers about fraud detection.

Use Cases

Best For

Researchers conducting literature reviews on graph-based fraud detection methods
Data scientists building fraud models for credit card or insurance claim data
Engineers implementing real-time fraud detection systems in e-commerce or fintech
Academics teaching courses on anomaly detection or applied machine learning
Practitioners exploring federated learning for privacy-preserving fraud detection
Teams investigating anti-money laundering or blockchain fraud detection techniques

Not Ideal For

Teams needing production-ready, plug-and-play fraud detection APIs or libraries
Practitioners seeking hands-on tutorials or step-by-step implementation guides without academic depth
Organizations with limited access to paid academic conferences or institutional subscriptions
Projects focused solely on operational deployment without time for literature review

Pros & Cons

Pros

Extensive Conference Coverage

Aggregates papers from top-tier conferences like KDD, AAAI, and WWW spanning decades, ensuring access to seminal and cutting-edge research in one place.

Multi-Domain and Methodological Breadth

Covers fraud detection across finance, e-commerce, social networks, and more, with diverse techniques from graph neural networks to federated learning, as highlighted in the structured listings.

Community-Driven and Updated

Encourages pull requests and is linked to similar awesome-lists, fostering active maintenance and expansion, as indicated by the 'PRs Welcome' badge and related collections.

Direct Resource Links

Provides direct links to PDFs and code implementations when available, saving time in sourcing materials, as seen in entries like DiG-In-GNN (2024) with code repositories.

Cons

No Practical Implementation Guidance

The repository lists papers without accompanying tutorials or deployment advice, forcing users to independently bridge the gap from research to application, which is not addressed in the README.

Accessibility and Quality Gaps

Many linked papers are behind paywalls or require institutional access, and there's no quality filtering or reviews, leaving users to assess relevance and impact on their own.

Academic-Only Focus

Excludes industry reports, blogs, or non-conference resources, limiting its utility for those seeking immediate, business-oriented solutions or real-world case studies.

Frequently Asked Questions

Related Projects

vinta

An opinionated list of Python frameworks, libraries, tools, and resources

Stars293,881

Forks27,742

Last commit2 days ago

awesome-machine-learning

A curated list of awesome Machine Learning frameworks, libraries and software.

Stars72,258

Forks15,417

Last commit3 days ago

awesome-awesomeness

A curated list of awesome awesomeness

Stars33,378

Forks3,592

Last commit1 year ago

data-science-ipython-notebooks

Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.

Stars29,020

Forks8,030

Last commit2 years ago

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub