A Comparative Study of Machine Learning Algorithms for Early Cost Estimation of Building Projects in Nepal

Abstract

Construction cost estimation is crucial to a project’s success, but because of the many variables that impact it, it is challenging to make an accurate prediction. Traditional methods are being used for preliminary cost estimation in the construction industry of Nepal. There still exists the problem of cost overrun, and time delay due to incorrect cost budgeting. This study aims to analyze a modern method of preliminary cost estimation in Nepal to prove its efficiency over the traditional method. In this work models such as Linear Regressor, Decision Tree Method, Random Forest method, Artificial Neural Networks, Support Vector Machine, Boost method, Extra tree method, Voting Regression, and Stacking method are used. Regarding the datasets, the buildings that were used are Educational Building, Commercial Building, Hospital Building, Residential Building, Public Building, Official Building, and Hotel Building having 0 to 2 basements ranging above 1 crore. The input features were taken from the literature review, and validated by expert opinion, and after successfully conducting pilot testing, the survey questionnaire was distributed among contractors and consultants. Data preprocessing was done and training and testing data sets were developed. The model was developed for nine algorithms. Mean absolute error (MAE), Mean square error (MSE), Root mean square error (RMSE), and R square value are used as evaluation metrics. In the evaluation of various regression models, three stand out as the most promising for predicting the target variable. The Decision Tree model exhibited remarkable performance with an MSE of 0.088575, an MAE of 0.104625, an RMSE of 0.297615, and an R² of 0.876170. Similarly, the Extra Tree model closely followed with an MSE of 0.088601, an MAE of 0.102909, an RMSE of 0.297659, and an R² of 0.876134. The Voting Model with an MSE of 0.105035, an MAE of 0.222807, an RMSE of 0.324091, and an R² of 0.853159. This study also opens the path for the exploration of other models and motivate to follow the trends of machine learning in the present era.