A comparative evaluation of decision trees and expert intuition to predict durations in the predesign phase

Construction projects are often subject to scheduling errors caused by uncertainty and systematic planning fallacies. This paper evaluates the prediction accuracy of CatBoost expert intuition predict duration public construction in predesign phase. The authors use a dataset city New York (USA) with 367 projects. Both compared performance indicator Mean Absolute Error (MAE) absolute preferrence. results show high outliers intuition, while indicates more consistent predictions. From practical perspective, especially uncertain events has advantages.