<![CDATA[The descriptive management of customer complaint data has made it difficult for the company to identify complaint patterns and forecast complaint trends as a basis for decision-making. This study aims to develop a Customer Complaint Monitoring Dashboard based on K-Means Clustering and Moving Average at PT Angkasa Pura Indonesia Site SUB. The data used consist of historical customer complaint records from January 2023 to September 2024. The K-Means Clustering method was applied to group service categories according to complaint priority levels, while the Moving Average method was used to forecast trends in the number of customer complaints. The results show that the optimal number of clusters selected using the Elbow Method was four clusters (K = 4). Evaluation using the Silhouette Score produced a value of 0.7228 for K = 4, indicating good clustering quality. In the forecasting process, the three-period Moving Average method, MA(3), achieved a Mean Absolute Percentage Error (MAPE) of 26.07% and was therefore selected as the best forecasting model. All analytical results were subsequently implemented in a Laravel-based monitoring dashboard capable of presenting information visually and interactively to support service monitoring and data-driven decision-making.]]>
Copyrights © 2026
