A Novel Continuous KNN Prediction Algorithm to Improve Manufacturing Policies in a VMI Supply Chain

This paper examines and compares various manufacturing policies which a manufacturer may adopt so as to improve the performance of a supply chain under vendor managed inventory (VMI) partnership. The goal is to maximize the combined cumulative profit of supply chain while minimizing the relevant inventory management costs. The supply chain is a two-level system with a single manufacturer single retailer at each level, in which the manufacturer takes the responsibility of overall inventories of supply chain. A base system dynamics (SD) simulation model is first employed to describe the dynamic interactions between the variables and parameters of manufacturer and retailer under VMI. Then, the mentioned policies are constructed using the base SD model that lead us to differentiate the behavior of supply chain members for each policy within the same duration of time. In this paper, we use continuous K-nearest neighbor (CKNN) as one of the instance-based learning methodologies to predict the best manufacturing rates. This algorithm effectively increases the combined profit of supply chain in comparison with other two policies discussed in this study. Accordingly, a numerical example along with a number of sensitivity analyses are conducted to evaluate the performance of proposed policies.