Published Work

Explores how machine learning and AI models can be applied to demand forecasting in supply chains, quantifying the downstream impact on inventory levels, carrying costs, and service levels across MENA distribution networks.

Investigates how BI systems and data dashboards translate into measurable supply chain performance gains — including lead time reduction, order accuracy, and cost-to-serve improvements across diverse industry sectors.

Benchmarks various ML algorithms — from ARIMA to gradient boosting and LSTM networks — on retail demand forecasting tasks, measuring accuracy, training cost, and adaptability to seasonal patterns in developing-market retail chains.

Evaluates the operational and strategic impact of real-time IoT tracking across logistics and warehousing, examining how sensor data and connected devices improve transparency, reduce disputes, and enable proactive exception management.