A Machine Learning-Enhanced Software Framework for Intelligent Inventory Monitoring and Demand Forecasting of Perishable Goods: Evidence from Developing Economy SMEs

In many developing countries, poor management of perishable goods causes significant economic and nutritional losses. For example, food waste rates in sub-Saharan Africa are over 50%. Most smart inventory systems are designed for large companies with plenty of data and strong infrastructure, so small and medium-sized businesses (SMEs) often have limited options. This study introduces a machine learning-based software framework for smarter inventory monitoring and demand forecasting of perishable goods, tailored for retail SMEs with limited resources. The framework was tested using real-world data from Sierra Leone. Five forecasting models were compared: Linear Regression (as a baseline), Random Forest (ultra-tuned), XGBoost (ultra-optimised), a Stacking Ensemble, and a Hybrid XGBoost-LSTM model.