Enhancing Supply Chain Resilience Using Machine Learning in SAP IBP: A Case Study in Automotive Manufacturing

Supply chain disruptions, exacerbated by global uncertainties, demand agile planning tools. This paper presents a machine learning (ML)-enhanced demand sensing model integrated into SAP Integrated Business Planning (IBP) to improve supply chain resilience in automotive manufacturing. We propose a hybrid ML architecture combining Long Short-Term Memory (LSTM) networks for temporal pattern recognition and XGBoost for feature importance analysis. Deployed in a tier-1 automotive supplier, the model reduced stockouts by 30% while maintaining 98% service levels. The study highlights technical implementation steps, quantifies performance gains, and provides actionable insights for scaling ML-driven planning in SAP IBP.