Data-Driven Analysis for Facility Management in Higher Education Institution

Abstract

Planned Preventive Maintenance (PPM) and Unplanned Maintenance (UPM) are the most common types of facility maintenance. This paper analyzes current trends and status of Facility Management (FM) practice at higher education institutions by proposing a systematic data-driven methodology using Natural Language Process (NLP) approaches, statistical analysis, risk-profile analysis, and outlier analysis. This study utilizes a descriptive database entitled “Facility Management Unified Classification Database (FMUCD)” to conduct the systematic data-driven analyses. The 5-year data from 2015 to 2019 was collected from eight universities in North America. A preprocessing step included but was not limited to identifying common data attributes, cleaning noisy data, and removing unnecessary data. The outcomes of this study can facilitate the decision-making process by providing an understanding of various aspects of educational facility management trends and risks. The methodology developed gives decision makers of higher education institutions, including facility managers and institution administrators, effective strategies to establish long-term budgetary goals, which will lead to the enhancement of the asset value of the institutions.