A SYSTEMATIC LITERATURE REVIEW OF BIG DATA ANALYTICS TECHNIQUES APPLICATIONS IN CONSTRUCTION COST FORECASTING
Jesse Amadosi Emmanuel, Olajide Olamilokun
This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
The capacity of the construction industry to generates massive data – popularly termed big data – has become a mainstream subject. Consequently, the implementation of modern analytical techniques on these big data is envisioned to improve the accuracy of cost forecasted at the project conceptual phase. Yet, with growing trend in analytical techniques, cost forecasted for most project is still fraught with inaccuracies. To address this problem, this study examines how the adoption of big data analytics techniques can be leveraged upon to improve the accuracy of cost forecasted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol. From a total of 205 articles retrieved from EBSCOhost, Google Scholar, Science Direct, and Dimension databases and ASCE library, 79 articles published between 1976 and 2023 were considered for the study. From the analysis of the extant literature, four main components are outlined as results; first the review establish that predictive analytics is predominantly employed to forecast cost among other approaches like descriptive and prescriptive analytics. Secondly, the nature of cost drivers employed for forecasting raises concern on the need to combine unstructured and structured data to forecast cost. Thirdly, with regards to methodology adopted for cost estimation, the result of the analysis indicate that the quantitative methodology has been applied majorly to forecast cost in light of the intervention of modern analytical tools. Lastly, the review also highlights where data management comes in within the forecasting process harmonised from literature. The review ends with the recommendation that both structured and unstructured data be effectively managed on the basis of completed projects using robust analytical techniques.
Big data analytics, techniques, cost forecasting, accuracy, data management.