4 datasets found

The dataset used in this paper is a large-scale dataset for automatic detection of cash-out fraud, with more than 100 million training samples.

Return-freight insurance dataset, containing accounts that have filed a claim over the past months, with device UMIDs used by these accounts in the past 40 days as graph nodes.

A public credit card transaction dataset from Kaggle website, which contains 492 frauds out of 284,807 transactions.

The dataset used in this paper is a publicly available credit card transactions dataset, anonymized and transformed using Principal Component Analysis (PCA).