Big data analytics for predictive maintenance in maintenance management

Abstract

Purpose: This research attempts to highlight the concept of big data analytics in predictive maintenance for maintenance management of government buildings in Malaysia. Design/methodology/approach: This study uses several empirical analyses such as vector autoregression (VAR), vector error correction model (VECM), ARMA model and Granger causality to analyse predictive maintenance by using big data analytics concept. Findings: The results indicate that there are strong correlations among these variables, which indicate reciprocal predictive maintenance of maintenance management job function. The findings also showed that there are significant needs of application of big data analytics for maintenance management in Putrajaya, Malaysia, to ensure the efficient maintenance of government buildings. Originality/value: The conducted case study has demonstrated the empirical perspective which streamlines with the big data analytics' concept in maintenance, especially for analytics' support with appropriate empirical methodology.