Predicting the Impact of Construction Rework Cost Using an Ensemble Classifier

Predicting construction cost of rework (COR) allows for the advanced planning and prompt implementation appropriate countermeasures. Studies have addressed causation different impacts COR but not yet developed robust predictors required to detect rare items with a high-cost impact. In this study, two ensemble learning methods (soft hard voting classifiers) are utilized nonconformance reports (NCRs) compared literature on nine machine (ML) approaches. The classifiers leverage advantage ML approaches, creating estimator that is responsive underrepresented impact classes. results demonstrate improved performance adopted in terms accuracy predictor increases reliability estimation, enabling dynamic variation analysis thus improving cost-based decision making.