Credit Card Fraud Detection Dataset

Dataset Overview

Dataset Name

Credit Card Fraud Detection

Dataset Description

This dataset contains transaction records of European credit‑card users from September 2013. It covers two days of transactions, with 492 fraudulent cases out of a total of 284,807 transactions. The dataset is extremely imbalanced, with fraudulent transactions (positive class) constituting 0.172 % of all records.

Dataset Features

• Input Variables: The dataset includes only numerical variables that have been transformed via PCA. Original features and additional background information are not provided due to privacy concerns.
• Feature Details:
  • V1–V28: Principal components obtained via PCA.
  • Time: Seconds elapsed between each transaction and the first transaction in the dataset.
  • Amount: Transaction amount, usable for example‑based cost‑sensitive learning.
  • Class: Response variable; 1 indicates fraud, 0 indicates legitimate transaction.

Data Source

The dataset was collected and analyzed jointly by Worldline and the Machine Learning Group at Université Libre de Bruxelles (ULB) for big‑data mining and fraud‑detection research.