Application of Latent Semantic Analysis for Conceptual Cost Estimates: Assessment in the Construction Industry

Abstract

Conceptual cost estimates represent the first benchmark upon which owners define their financial capability of performing a construction project. Consequently, the accuracy and quality assessments of these estimates are crucial. This paper proposes an automated conceptual cost estimate assessment model through Latent semantic Analysis (LSA). The use of LSA in the construction industry has rarely been implemented, which deprives this industry from utilizing its strengths to facilitate decision making. The research methodology adopted (1) utilizes data from a set of completed construction projects; (2) proposes an automated LSA model for the assessment of conceptual cost estimates based on error ranges; and (3) compares the attained outcomes to previous researches in the literature review. The outcomes of the current research illustrate that LSA modeling performs accurately in assessing conceptual cost estimate making it a powerful tool for construction decision making.