Data-driven study on the achievement of LEED credits using percentage of average score and association rule analysis

Abstract

Developed by the U.S. Green Building Council, Leadership in Energy and Environmental Design (LEED) certifies green buildings into different grades according to the number of credit points each building has achieved. LEED managers often attempt to achieve as many credits as possible with limited budgets and resources. However, referring to the credit requirements alone does not help evaluate the difficulty in achieving those credits. Data on how LEED credits were achieved in previous projects may offer some insights, yet no research has quantitatively analyzed the previous records. This study aims to analyze LEED credit achievements in previous projects using data driven techniques and provide LEED managers with a better understanding on the achievements of individual credits and related credits. 1000 projects certified by LEED-NC v3 were collected as the case base. A measurement called the percentage of average score (PAS) was proposed to analyze how individual credits were attained in the past. Credits like MRc6 and MRc3 were discovered to have stringent requirements and were rarely achieved. In addition, relationships among credits were analyzed using association rule mining. Thresholds for support and confidence were identified by implementing a classification algorithm namely CMAR. Among 224 pairs of related credits that are suggested by USGBC, 50 pairs were identified as strongly related. In addition, 13 new pairs of related credits that have not been suggested by USGBC were discovered.