Room Maintenance Analysis using a Clustering Method

Abstract

This research explores an application of K-Means clustering to analyze hotel room maintenance operations, focusing on three key aspects: room analysis, type of work analysis, and workload balance among technicians. The study aims to identify patterns and inefficiencies in maintenance tasks, providing data-driven insights to optimize operational efficiency. The clustering analysis revealed that certain areas of the hotel, particularly specific towers, are prone to more frequent maintenance requests, indicating a need for tailored maintenance strategies. Additionally, the analysis of work types highlighted the varying time requirements for different tasks, enabling more effective resource allocation. Finally, the workload analysis identified imbalances in task distribution among technicians, suggesting opportunities to improve workforce efficiency. The findings were presented to the hotel’s management team, who confirmed that the results accurately reflected their current operational challenges. Management recognized the potential of K-Means clustering as a valuable tool for enhancing room maintenance processes, ultimately leading to improved service quality and guest satisfaction. This research demonstrates the practical application of machine learning techniques in the hospitality industry, offering a novel approach to optimizing hotel maintenance operations.

Keywords: Hotel Room Maintenance, K-Means Clustering, Room Analysis, Type of Work Analysis, Workload Balance

View PDF