Estimating contract value using structural parameters: a machine learning approach with data preprocessing

In this study, contract price in public construction tenders are predicted using structural project parameters. The variables applied in the study are created by adding the quantities of columns, shear walls, and beams to variables commonly used in the literature for cost estimations. Six different machine learning algorithms are employed as machine learning algorithms. Preprocessing methods and a series of parameter optimizations are applied to enhance the predictive capability on datasets. These processes and the applied algorithms are evaluated with five different performance metrics. The SVM algorithm produced the best results, achieving an value of 0.8966, MAPE of 23.70, NSE of 0.8956, MAE of 0.4849, and RMSE of 0.6989. This study contributes to the literature by developing machine learning models and data analysis processes for contract price approaches.