Improved similarity measure in case-based reasoning: a case study of construction cost estimation

Abstract

Purpose

Applied a hybrid approach using genetic algorithms (GAs) for a case-based retrieval process in order to increase the overall improved cost accuracy for a case-based library. The paper aims to discuss this issue.

Design/methodology/approach

A weight optimization approach using case-based reasoning (CBR) with proposed GAs for developing the CBR model. GAs are used to investigate optimized weight generation with an application to real project cases.

Findings

The proposed CBR model can reduce errors consistently, and be potentially useful in the early financial planning stage. The authors suggest the developed CBR model can provide decision-makers with accurate cost information for assessing and comparing multiple alternatives in order to obtain the optimal solution while controlling cost.

Originality/value

The system can operate with more accuracy or less cost, and CBR can be used to better understand the effects of factor interaction and variation during the developed system’s process.

Citation

Hyung, W.-G., Kim, S. and Jo, J.-K. (2020), "Improved similarity measure in case-based reasoning: a case study of construction cost estimation", Engineering, Construction and Architectural Management, Vol. 27 No. 2, pp. 561-578. https://doi.org/10.1108/ECAM-01-2019-0035