Comparing Cost Prediction Methods for Apartment Housing Projects: CBR versus ANN

Abstract

Prediction of the cost estimation of apartment house is an important task in the management of construction projects. This study aims at illustrating the compared results of the application of two different approaches which are used case-based reasoning (CBR) and artificial neural networks (ANN) techniques. This study is conducted by using the same 540 cases which are obtained in Korea. 30 cases among the data are used for testing. Testing error rates of 3.69% in the CBR and 6.52% in the ANN were obtained. Results showed that CBR can produce slightly more accurate results and achieve higher computational efficiency than ANN. If the use of CBR and ANN is understood better, as a result, cost estimation can be predicted with reasonability, all parties involved in the construction process could save considerable money. © 2005, Architectural Institute of Japan. All rights reserved.