There is a prevalence of poor building maintenance practices in both the public and private sectors in Malaysia. To improve the current state of maintenance, effective decisions must be made by the building stakeholders. Unfortunately, the decision-making process for building maintenance in Malaysia is still traditional. The decisions are usually made based on the latest maintenance inspection without taking into consideration the trend of past data. This limits the building maintenance strategy to corrective (reactive) and preventive (expensive). Data-driven decisions improve building operations and create better predictive maintenance programs because the stakeholders can instantly identify problems and effectively act. Maintenance analytics is a structured and technological approach used to extract information from data and has proven to be an acceptable tool to improve building operation and maintenance. It is used to determine “what has happened?”, “why it happened?”, “what will happen?”, and “what needs to be done?” to enable decision-makers to take appropriate actions. In a country like Malaysia where maintenance practice is not data-driven, there is a need to identify the techniques to improve the maintenance process (especially decision-making). Therefore, this study aims to identify the various analytical techniques applied in existing maintenance analytics studies and determine the current direction of maintenance analytics studies. A comprehensive literature review was done to understand maintenance analytics, types of data and its sources, and the analytical techniques applied. Findings from the literature review revealed that the major data sources are CMMS, BIM, IoT, BAS. It was also noticed that the type of data used influenced the choice of analytical technical techniques. In addition, it was noted that certain studies did not use the major data sources and analytical techniques, and other studies used more than one data source. Overall, the general direction of the maintenance analytics studies was building performance and operation, end-user complaints, and work orders. There is a gap in the application of maintenance analytics to cost-effective decision-making in building maintenance. Which is recommended as the direction for future studies.

No abstract

No abstract