aaronzeller/small-aml-data

## Dataset Credits

This project uses the **IBM Transactions for Anti Money Laundering (AML)** synthetic dataset, published by **Erik Altman** and collaborators at IBM Research.

Original dataset source:
- Kaggle: https://www.kaggle.com/datasets/ealtman2019/ibm-transactions-for-anti-money-laundering-aml
- IBM Research publication: https://research.ibm.com/publications/realistic-synthetic-financial-transactions-for-anti-money-laundering-models
- IBM AML-Data repository: https://github.com/IBM/AML-Data

The dataset is synthetic and was created to support AML research and benchmarking.
Please refer to the original authors and sources above for full dataset documentation, background, and citation guidance.

### License and Modifications

The underlying dataset is released under the **Community Data License Agreement – Sharing – Version 1.0 (CDLA-Sharing-1.0)**:
- https://cdla.dev/sharing-1-0/

Our project uses a **modified/prepared version** of the dataset for database initialization and application integration.
These modifications include preprocessing and schema adaptation for our dashboard and backend workflow, such as:
- replacing bank IDs with readable bank names
- normalizing column names
- preparing the dataset for one-time PostgreSQL initialization

This project does **not** claim ownership of the original dataset.
Credit for the underlying AML dataset remains with the original creators and publishers.