An Approach to Optimize Future Inbound Logistics Processes Using Machine Learning Algorithms

The manufacturing industry is in rapid change due to the increasing amount of market changes. Therefore, the accuracy of planning is critical for the manufacturers since it reflects on the global supply chain network. For inbound logistics, a variety of goods comes from different suppliers and locations to the manufacturing plants. Planning these inbound logistics relies on product readiness, manufacturing plant planning, procurement, and their continually changing information. This paper focuses on machine learning algorithms, such as K -nearest neighbors (KNN), decision trees, Support Vector Machine (SVM), and Artificial Neural Network (ANN), to improve planning inbound logistics processes. These algorithms that monitor and train on customer preferences, weather, regulations, and other complex planning factors in the planning process. In the planning process, half of the time is consumed on preparing and collecting the information, and the gained knowledge is not used efficiently. Therefore, this paper proposes an approach to optimize future inbound logistics processes using machine learning algorithms such as kNN, decision trees, SVM, and ANN.