IEEE-CIS Fraud Detection Dataset
A public fraud detection dataset on Kaggle provided by the IEEE Computational Intelligence Society and the company Vesta. It contains a large number of transaction records along with shared attributes such as card numbers, addresses, and devices, and is commonly used in graph neural network and machine learning research on fraud detection.
Timeline (last 90 days)
A developer built a benchmark task in the Kaggle Benchmarking Challenge, using the IEEE-CIS fraud detection dataset to test Gemma 4 31B (google/gemma-4-31b) on its ability to judge whether a transaction is suspicious based solely on textualized graph structure information.
The 53% in the neighbor identification task is a fraud-neighbor proxy score, because the IEEE-CIS dataset does not provide verified fraud ring membership labels or ring leader labels, and this score cannot be regarded as evidence that the model can identify real fraud rings or their leaders.
All Facts (2)
The 53% in the neighbor identification task is a fraud-neighbor proxy score, because the IEEE-CIS dataset does not provide verified fraud ring membership labels or ring leader labels, and this score cannot be regarded as evidence that the model can identify real fraud rings or their leaders.
50%UnverifiedA developer built a benchmark task in the Kaggle Benchmarking Challenge, using the IEEE-CIS fraud detection dataset to test Gemma 4 31B (google/gemma-4-31b) on its ability to judge whether a transaction is suspicious based solely on textualized graph structure information.
50%