Predictive Inventory Analytics and Demand Forecasting in Malaysian Electronics Manufacturing

This study investigates the role of predictive inventory analytics in enhancing demand forecasting accuracy within Malaysia’s electronics manufacturing sector. As global supply chains become increasingly volatile, electronics manufacturers face challenges in managing inventory for components with long lead times and fluctuating demand. Leveraging machine learning (ML) models such as XGBoost, LSTM, and Random Forest, this research evaluates how predictive analytics can reduce inventory waste, improve responsiveness, and support strategic planning. Findings from case studies and data analysis reveal that ML-driven forecasting significantly improves inventory performance, especially during periods of global disruption and product lifecycle transitions.