What is the Financial Fraud Training Container?

The Financial Fraud Training container provides the capabilities to train Graph Neural Network (GNN) and XGBoost models to predict fraud scores of credit card transactions. Based on user provided training configuration, the container first builds a GNN model that produces embeddings for credit card transactions, and then the container uses the transaction embeddings to train an XGBoost model to predict fraud scores of the transactions. The container encapsulates the complexity of creating the graph in cuGraph. Once the graph is created, the GNN model is trained and used to produce the embeddings that are then feed to XGBoost.

Applications

Financial losses from worldwide credit card transaction fraud are projected to reach more than $403 billion over the next decade. Traditional fraud detection methods, which rely on rules-based systems, or statistical methods, are reactive and increasingly ineffective in identifying sophisticated fraudulent activities. As data volumes grow and fraud tactics evolve, financial institutions need more proactive, intelligent approaches to detect and prevent fraudulent transactions.

1. Getting Started

Prerequisites

• Obtain an NVIDIA/NGC API key
• CUDA 12.6+ drivers installed

Quick Setup

1. Authenticate with NGC. Obtain an API key from NGC, then log in to the NVIDIA container registry:

   docker login nvcr.io --username '$oauthtoken' --password $NGC_API_KEY
   

   Replace $NGC_API_KEY with your actual API key, or set it as the NGC_API_KEY environment variable.

2. Pull the Docker image:

   docker pull nvcr.io/nvidia/cugraph/financial-fraud-training:2.0.0
   

3. Run the training container:

   docker run -it --rm --name=financial-fraud-training \
     --gpus "device=0" \
     -v <YOUR_GNN_DATA_DIR>:/data \
     -v <DIR_TO_SAVE_TRAINED_MODELS>:/trained_models \
     nvcr.io/nvidia/cugraph/financial-fraud-training:2.0.0
   

   Replace <YOUR_GNN_DATA_DIR> and <DIR_TO_SAVE_TRAINED_MODELS> with the actual paths on your system where your GNN data is located and where trained models should be saved.

   Command breakdown:

   • -it — run the container interactively.
   • --rm — automatically remove the container when it exits.
   • --name=financial-fraud-training — names the container.
   • --gpus "device=0" — exposes GPU 0 to the container.
   • -v <YOUR_GNN_DATA_DIR>:/data — mounts your GNN data directory into the container.
   • -v <DIR_TO_SAVE_TRAINED_MODELS>:/trained_models — mounts a directory for saving trained models.

For the full walkthrough, see the Getting Started Guide.

2. Documentation

For comprehensive documentation — including configuration, data preparation, training, and inference:

• Full Documentation: https://docs.nvidia.com/nim/financial-fraud-training/latest/index.html

3. System Requirements

Software Requirements

Hardware Requirements

License

This container is licensed under the NVIDIA AI Product Agreement. By pulling and using this container, you accept the terms and conditions of this license.