Maulyda Nurannisa, Apif Miptahul Hajji, Aisyah Larasati, Yuh Wen Chen
The concept of project management helps minimize the risk of loss for project managers. This study aims to develop a model for evaluating the performance of architectural work by combining the Earned Value Management (EVM) and Support Vector Machine (SVM) models. The Earned Value method has advantages in forecasting project scheduling and planning. In this research, forecasting is done with the help of machine learning to increase the accuracy of project completion time prediction. This research uses the architectural data study object of the Lecture Building Project (GKB UM). This study indicates that the performance of the architectural work of GKB UM has been delayed with a schedule variance (SVt) value of -13.53 weeks. In developing the prediction model using the Support Vector Machine algorithm, the most optimal parameter results are using the Radial Basis Function (RBF) kernel type, complexity (C) 150, and gamma (y) 0.01 with a Root Mean Square Error (RMSE) value of 0.565. Thus the prediction of project completion has a difference of 4 weeks. Project delays were caused by weather problems, Tower Crane (TC) damage, incompatibility of Homogeneous Tile (HT) work, and changes in Bill of Quantity (BOQ). © 2021 Author(s).
Industrial Engineering Study Program, State University of Malang, Malang, Indonesia; Civil Engineering Study Program, State University of Malang, Malang, Indonesia; Department of Information Management, Da-Yeh University, Chang Hwa, Taiwan
