English

Downstream Task-Oriented Generative Model Selections on Synthetic Data Training for Fraud Detection Models

Machine Learning 2024-01-03 v1 Artificial Intelligence

Abstract

Devising procedures for downstream task-oriented generative model selections is an unresolved problem of practical importance. Existing studies focused on the utility of a single family of generative models. They provided limited insights on how synthetic data practitioners select the best family generative models for synthetic training tasks given a specific combination of machine learning model class and performance metric. In this paper, we approach the downstream task-oriented generative model selections problem in the case of training fraud detection models and investigate the best practice given different combinations of model interpretability and model performance constraints. Our investigation supports that, while both Neural Network(NN)-based and Bayesian Network(BN)-based generative models are both good to complete synthetic training task under loose model interpretability constrain, the BN-based generative models is better than NN-based when synthetic training fraud detection model under strict model interpretability constrain. Our results provides practical guidance for machine learning practitioner who is interested in replacing their training dataset from real to synthetic, and shed lights on more general downstream task-oriented generative model selection problems.

Keywords

Cite

@article{arxiv.2401.00974,
  title  = {Downstream Task-Oriented Generative Model Selections on Synthetic Data Training for Fraud Detection Models},
  author = {Yinan Cheng and Chi-Hua Wang and Vamsi K. Potluru and Tucker Balch and Guang Cheng},
  journal= {arXiv preprint arXiv:2401.00974},
  year   = {2024}
}

Comments

The following article has been accepted by ICAIF22, Synthetic Data for AI in Finance; see https://sites.google.com/view/icaif-synthetic-2022/program

R2 v1 2026-06-28T14:06:27.980Z