AN OPTIMIZE DISTRIBUTION USING HYBRID MODEL: CUSTOMER SEGMENTATION AND TRAVELING SALESMAN PROBLEM

Abstract

The research is motivated by issues encountered in the process of distributing products such as shifts in consumption patterns post the Covid-19 pandemic, and potential losses arising from the process of delivering food to customers. The objective of this study is to identify customer segmentation in order to enhance the efficiency of the distribution process and to identify the most efficient route for the distribution process. During the segmentation process, it is critical to identify the suitable attributes. Moreover, once the attributes have been identified, the segmentation process will be implemented using the K-Means method. Subsequently, the optimization process will be executed using the Traveling Salesman Problem. The result showed the segmentation process enable to find the optimal number of cluster, this is shown by reducing the number of clusters from 14 clusters to 9 clusters. Furthermore, the research outcomes regarding the optimization process demonstrate that the model is indeed optimal. The results indicate a 15.16% reduction in the overall travel distance, resulting in a decrease from 3,386.5 kilometers to 2,940.8 kilometers.

Keywords : distribution process, customer segmentation, k-means, traveling salesman problem