Graph-Based Explainable AI Framework for Financial Fraud Detection Using Graph Neural Networks

A graph-based explainable AI framework that detects financial fraud with graph neural networks.

A graph-based explainable AI framework that detects financial fraud with graph neural networks. It is offered as a reference project: a complete, worked example of how a system like this is designed, built and evaluated, so that a developer can study it, run it and learn from it.

It suits learners who want to work with neural networks end to end: preparing datasets, designing and training a model, tuning it, evaluating it properly and explaining the outcome.

The main parts are explanations of each result (feature importance or visual evidence), dataset preparation and augmentation, model design and training, evaluation with standard metrics, plus error analysis, and a simple interface or API to try the model. The reference build uses PyTorch Geometric, SHAP, Python, PyTorch, and TensorFlow, with a clear project structure, setup instructions and sample data so that it can be run and extended.