ENHANCING SUPPLY CHAIN AGILITY AND SUSTAINABILITY FOR LOGISTICS

It is specifically concerned with innovative development in supply chain management and application of the same in machine learning to enhance dynamism and sustainability in the same. The world is highly complex at the moment and this translates into supply chain management requiring agents to be more responsive to shocks while at the same maximizing the sustainability gains. For the selection of features and class labels as well as to overcome the problem of overfitting Lasso and Elastic Net regression have been employed, for segmentation of data K-means has been used and at last, for the detection of anomalies DBSCAN has been used. As well, in the case of enhancing the most optimal paths for logistics usage, Convolutional Neural Networks (CNNs) are used. Therefore, these methods are helpful to enhance the supply chain and livelihood performance not to overfit, to make better decisions, and to establish a good risk monitoring system. For the existing literature, this research operates to understand how advanced analytics can be adopted by supply chain management within this significantly unpredictable field.