MODEL ESTIMASI BIAYA DENGAN COST SIGNIFICANT MODEL DAN ARTIFICIAL NEURAL NETWORK PROYEK PENINGKATAN JALAN ASPAL DI YOGYAKARTA

Abstract

The need for an analytical method that may provide an accurate project cost estimation with minimal data availability becomes very necessary. Therefore, this research was conducted to determine and compare the cost estimation model based on the Cost Significant Model (CSM) and Artificial Neural Network (ANN) with two modeling approaches, ANN-1 and ANN-2. The models were developed based on 28 data of road improvement projects in Yogyakarta from the year 2010 until 2019. The analysis results show that the ANN-2 provides the best validation compared to the ANN-1 and the CSM model. The value of Mean Absolute Percentage Error (MAPE) of ANN-1 with the 3-8-1 net scheme provides a value of 12.687%, while that of ANN-2 with 10-15-1 net scheme is 8,132% and the MAPE value of the CSM model produces a value of 14.757%.