A synthetic dataset of SWIFT financial transactions designed for federated learning applications. The dataset is intended for developing and testing fraud detection models in a distributed, privacy-preserving training environment. It was sourced from the Kaggle platform, but specific authorship, creation date, and update history are not provided.
Use Cases
- Train federated fraud detection models based on synthetic SWIFT transaction patterns.
- Benchmark privacy-preserving machine learning algorithms based on financial transaction data.
- Simulate distributed learning scenarios for financial security based on the described transaction dataset.
Strengths
- Designed specifically for the federated learning paradigm, a key feature mentioned in the title.
- Synthetic nature, as stated in the description, allows for controlled experimentation without real-user privacy concerns.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Row count is unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
Provenance
- Source
- Kaggle
- Collection Method
- Synthetically generated, as indicated by the description.