Abstract

Cost and time domination are interminable challenges in construction project management, often intensify by skilled labor shortages and the limited availability of high-technology equipment. This study develops a predictive analytics framework for AL Baraka Enterprises, Islamabad, manipulating traditional operational data to forecast project cost and schedule deviations. Using machine learning, we processed and analyzed a dataset with many variables, including baseline budgets, actual spending, planned and actual timelines, workforce skill distribution, equipment utilization rates, procurement lead times, supplier performance, and environmental conditions. The study of important factors found that a lack of skilled workers and advanced equipment being down were two of the main reasons why projects went off track. These two factors accounted for around 32% and 27% of the predicted variation, respectively. To fix these problems, a trial version of a decision support dashboard was made to keep track of risks in real time and help deal with them before they get worse. The research demonstrates that including manpower and equipment constraints into predictive analytics significantly enhances cost management and ensures timely completion of building projects.

Keywords: Predictive analytics, Construction management, Skilled labor shortage, Equipment availability, Machine learning, Cost optimization, Schedule forecasting