Improving Estimate at Completion (EAC) Cost of Construction Projects Using Adaptive Neuro-Fuzzy Inference System (ANFIS)
Earned Value Management (EVM) is well-known technique for measuring project performance and progress. Due to EVM's attitude to combining cost and time performance simultaneously, project performance can be forecasted accurately and this plays a vital role in the future of the projects. In the current study, the authors employed Adaptive Neuro-Fuzzy Inference System (ANFIS) as a powerful prediction tool to forecast completion cost of the projects considering the percentage of risk for qualitative variables and comparing it with other types of Neural Networks. Since the network structure is usually tuned based on the obtained results, network optimization procedure is applied using a conventional method for estimating cost-caused project breakdown. The results showed ANFIS had a suitable performance (MSE=0.0003) and based on the sensitivity analysis, EV is recognized as the most sensitive factor in the project. This paper improves the general estimate at completion formula by taking uncertain conditions into account.