Big Data In Construction Waste Management: Prospects And Challenges

Abstract

‘Big data’ has been rapidly sprawling in various research disciplines such as biology, ecology, medical science, business, finance, and public governance but rarely in construction waste management (CWM). The CWM community around the world generally relies on ‘small data’ collected via active solicitation such as sampling and ethnographic methods. This small data is intrinsically limited by its inability to account for the totality of CWM and research findings generated from the small data cannot be accepted with a high level of confidence. With the growing interests in big data, it can be reasonably expected that the waste management community will augment efforts to develop big data and its analytics. However, the efforts are currently constrained by the limited knowledge to do so. This research aims to provide a synoptic overview of the prospects and challenges of big data in CWM. It adopts an inductive, qualitative case study method whereby the empirical data is collected using an ethnographic–action-meta-analysis research approach and triangulated with data from literature, ongoing debate, and other sources. The paper offers some insights on big data acquisition, storage, analytics, implementation, and challenges. Although having a focus on waste management in the construction sector, the insights generated from this study can be of value to general waste management research, which suffers from the same problems of erratic and poor quality data as CWM.