Credit Card Transactions Synthetic Data Generation

This dataset is a collection of synthetic credit card transaction data generated for the purpose of training and testing machine learning models for credit card fraud detection and risk assessment. The data is designed to mimic the characteristics of real credit card transactions while ensuring privacy and compliance with data protection regulations such as the General Data Protection Regulation (GDPR).

Dataset Details:

-Size: The dataset contains a total of 3 files:
Credit card transactions with 1,785,308 transactions.
Customer profiles with 5,000 customers
Terminal profiles with 100 terminals

-Features: Each transaction record includes a variety of features commonly associated with credit card transactions, including transaction amount, merchant category code, time of transaction, and more.

-Labels: The dataset provides labels indicating whether each transaction is a legitimate or fraudulent transaction. This binary classification label is crucial for training and evaluating fraud detection models.

Potential Use Cases:

Machine Learning: This synthetic dataset is suitable for training and testing machine learning models, including anomaly detection and classification algorithms, to identify fraudulent credit card transactions.

Feature Engineering: Data scientists and analysts can use this dataset to explore feature engineering techniques for credit card transaction data, preparing it for modeling.

Model Evaluation: Researchers and practitioners can use this data to evaluate the performance of credit card fraud detection models and assess their accuracy, precision, recall, and other relevant metrics.

The Jupyter Notebooks used to generate this data are available here

Part of this work is based on the Fraud-Detection-Handbook

Disclaimer:

Please note that this dataset is entirely synthetic and for demonstration purposes only. It does not contain any real customer data, credit card numbers, or personally identifiable information (PII). Using this dataset responsibly and in compliance with applicable data privacy and ethical guidelines is essential.