Penerapan Big Data Analyst terhadap Pengiriman Barang Cacat Menggunakan Metode K-Means

Abstract

PT ID Express, a delivery service company, faces the challenge of high levels of damage to goods during the shipping process. This damage ranges from minor scratches or dents to severe damage such as breakage or destruction, which directly impacts customer satisfaction and the company's reputation. To address this issue, a data-driven approach capable of comprehensively identifying patterns and causal factors for damage is required. This study aims to analyze the types of damage to goods based on shipping data using the K-Means Clustering method. This method is used to group damaged goods data into several clusters based on the level of similarity in their characteristics. The results show that the damage data can be grouped into two main clusters: minor damage and major damage, each consisting of five dominant types of damage. Through this clustering, companies can gain a better understanding of frequently occurring damage patterns and can design more effective preventive measures. This research is expected to serve as a reference in the application of big data analysis in the logistics sector to improve service quality and reduce the risk of damage to goods during the distribution process.