<![CDATA[Accurate demand forecasting plays a crucial role in supporting inventory and sales strategies, particularly for Micro, Small, and Medium Enterprises (MSMEs) that often face resource constraints. This study aims to develop a predictive model using Artificial Neural Networks (ANN) to forecast product demand based on historical sales data. The ANN model is trained and evaluated using a structured experimental approach, adjusting parameters such as the number of hidden layers, learning rate, and epochs to identify the best-performing architecture. Evaluation metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and the coefficient of determination (R²) are used to measure model performance. The results demonstrate that the ANN model is capable of capturing complex nonlinear relationships in multidimensional data and producing accurate demand forecasts. The model particularly performs well in predicting demand trends for products in the Electronics and Household categories. These findings provide valuable insights for MSME stakeholders in optimizing inventory planning and making data-driven business decisions.]]>
Copyrights © 2025
