A Hybrid Framework for Dynamic Clustering and Anomaly Detection in SAP ERP Systems

The growing complexity of enterprise data in SAP ERP systems demands advanced methods for real-time anomaly detection and dynamic clustering optimization. Traditional clustering techniques, such as Standard K-Means, need to adapt to evolving data patterns, while existing AI/ML-based methods like GMM with EM and Self-Organizing Maps (SOM) face challenges in scalability and computational efficiency. This research proposes a hybrid model that integrates GMM, SOM, and adaptive K-Means to address these limitations, offering improved detection accuracy, precision, and recall. Tested on datasets of varying sizes (small, medium, large), the hybrid model consistently outperforms baseline methods, achieving up to 94% detection accuracy and high precision (95.5%) with strong scalability and interpretability. The model leverages distributed computing on a Spark cluster for efficient processing, ensuring seamless integration with SAP ERP environments. Results demonstrate the hybrid model’s ability to detect anomalies effectively, adapt to dynamic data streams, and provide actionable insights through intuitive visualizations. This comprehensive approach makes it a robust solution for maintaining data integrity and enhancing operational decision-making in increasingly complex and data-rich enterprise environments.