English

EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection

Machine Learning 2026-05-01 v2 Machine Learning

Abstract

Imbalanced datasets pose a difficulty in fraud detection, as classifiers are often biased toward the majority class and perform poorly on rare fraudulent transactions. Synthetic data generation is therefore commonly used to mitigate this problem. In this work, we propose the Clustered Embedding Diffusion-Transformer (EmDT), a diffusion model designed to generate fraudulent samples. Our key innovation is to leverage UMAP clustering to identify distinct fraudulent patterns, and train a Transformer denoising network with sinusoidal positional embeddings to capture feature relationships throughout the diffusion process. Once the synthetic data has been generated, we employ a standard decision-tree-based classifier (e.g., XGBoost) for classification, as this type of model remains better suited to tabular datasets. Experiments on a credit card fraud detection dataset demonstrate that EmDT significantly improves downstream classification performance compared to existing oversampling and generative methods, while maintaining comparable privacy protection and preserving feature correlations present in the original data.

Keywords

Cite

@article{arxiv.2603.13566,
  title  = {EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection},
  author = {En-Ya Kuo and Sebastien Motsch},
  journal= {arXiv preprint arXiv:2603.13566},
  year   = {2026}
}

Comments

Updated the first page to include the IEEE submission notice required for previously posted electronic preprint versions

R2 v1 2026-07-01T11:19:26.087Z