Optimizing Supply Chain Management with Neural Network and Machine Learning Techniques

This study focused on identifying the possible reduction in holding costs and minimizing stockout risk through utilizing machine learning models as; Long Short-Term Memory (LSTM), Artificial Neural Network (ANN) and Random Forest (RF) to improve supply chain management in textile sector. The research is based on rich data assets like historical sales information, weather factors and economic indexes, lead times (time intervals between emergence of need for a product until it becomes available in the store) along with supplier reliability and transportation details. However, the LSTM model that is capable of learning temporal dependencies performed with precision at the top with 97.76% accuracy which effectively learn elaborate patterns in our dataset. The ANN also accurately predicted at 94.50% accuracy that can capture complex relationships between different parameters of the supply chains. Although with slightly more false positive rate, RF showed highly robust performance using its ensemble approach (91.23% of accuracy). Every model will be trained and evaluated stringently where some performance metrics (accuracy, precision, recall, and F1 score) every epoch are considered. A comparative analysis of the different approaches used in this work show that LSTM scores higher precision and recall, essential for making forecasting over time where arithmetic predictions become harmful. ANN and RF offer stable across short terms prediction adjusting to operating context Businesses can improve their overall operational performance in dynamic and competitive market environments by incorporating these models to supply chain decision-making processes which result in efficient operations, lower inventory holding costs and reduce the risk of stockouts.