TY - GEN
T1 - Multi-Dimensional Quality Assessment of Synthetic Data across ERP Modules
AU - Febryanto, Kurnia Cahya
AU - Hidayati, Shintami Chusnul
AU - Sarno, Riyanarto
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - The rapid adoption of Enterprise Resource Planning (ERP) systems has highlighted critical data availability and quality challenges, particularly for predictive modeling and analytics. This research presents a comprehensive framework for synthetic data generation in ERP environments using advanced generative models, including GANs, CGANs, VAEs, Beta-VAEs, and Normalizing Flows. The framework encompasses data processing across Sales, Purchase, and Human Resource modules, implementing specialized loss functions for maintaining business rules and inter-module relationships. Experimental results demonstrate exceptional performance of the VAE architecture in Purchase and Human Resource modules with accuracy scores of 99.3 percent and 95.2 percent, respectively. In comparison, CGANs achieve 95.1 percent accuracy in Sales module synthesis.
AB - The rapid adoption of Enterprise Resource Planning (ERP) systems has highlighted critical data availability and quality challenges, particularly for predictive modeling and analytics. This research presents a comprehensive framework for synthetic data generation in ERP environments using advanced generative models, including GANs, CGANs, VAEs, Beta-VAEs, and Normalizing Flows. The framework encompasses data processing across Sales, Purchase, and Human Resource modules, implementing specialized loss functions for maintaining business rules and inter-module relationships. Experimental results demonstrate exceptional performance of the VAE architecture in Purchase and Human Resource modules with accuracy scores of 99.3 percent and 95.2 percent, respectively. In comparison, CGANs achieve 95.1 percent accuracy in Sales module synthesis.
KW - Enterprise Resource Planning
KW - Generative Models
KW - Quality Assessment
KW - Synthetic Data Generation
UR - https://www.scopus.com/pages/publications/105025400343
U2 - 10.1109/AIMS66189.2025.11229547
DO - 10.1109/AIMS66189.2025.11229547
M3 - Conference contribution
AN - SCOPUS:105025400343
T3 - 2025 IEEE International Conference on Artificial Intelligence and Mechatronics Systems, AIMS 2025
BT - 2025 IEEE International Conference on Artificial Intelligence and Mechatronics Systems, AIMS 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE International Conference on Artificial Intelligence and Mechatronics Systems, AIMS 2025
Y2 - 24 May 2025 through 25 May 2025
ER -