Predictive Analytics for Early-Stage Construction Costs Estimation

Abstract

Low accuracy in the estimation of construction costs at early stages of projects has driven the research on alternative costing methods that take advantage of computing advances, however, direct implications in their use for practice is not clear. The purpose of this study was to investigate how predictive analytics could enhance cost estimation of buildings at early stages by performing a systematic literature review on predictive analytics implementations for the early-stage cost estimation of building projects. The outputs of the study are: (1) an extensive database; (2) a list of cost drivers; and (3) a comparison between the various techniques. The findings suggest that predictive analytic techniques are appropriate for practice due to their higher level of accuracy. The discussion has three main implications: (a) predictive analytics for cost estimation have not followed the best practices and standard methodologies; (b) predictive analytics techniques are ready for industry adoption; and (c) the study can be a reference for high-level decision-makers to implement predictive analytics in cost estimation. Knowledge of predictive analytics could assist stakeholders in playing a key role in improving the accuracy of cost forecast in the construction market, thus, enabling pro-active management of the project owner’s budget.

Cost prediction of building projects using the novel hybrid RA-ANN model

“…Through analysis of 70 papers from the high-ranked journals, it is summarized that among all the machine learning techniques the percentages for hybrid models, fuzzy models, ANN, RA are 27%, 25%, 14%, 13% respectively which make up the top four. Lautaro et al (2022) conducted a comprehensive review of 46 studies on early project cost estimation and prediction analysis. This review shows that ANN, case-based reasoning (CBR), multiple regression analysis (MRA), boosting regression trees (BRT) and support vector machine (SVM) are the five main modeling techniques, which were used in 48%, 26%, 22% and 4% of the studies, respectively.…”

“…Through analysis of 70 papers from the high-ranked journals, it is summarized that among all the machine learning techniques the percentages for hybrid models, fuzzy models, ANN, RA are 27%, 25%, 14%, 13% respectively which make up the top four. Lautaro et al . (2022) conducted a comprehensive review of 46 studies on early project cost estimation and prediction analysis.…”

An integrated DEMATEL and system dynamic model for project cost prediction

“…Cost issues that affect the owner cover the variation of the contract cost from the anticipated cost during the planning phase (cost deviation) and the change in the contract cost at the project's completion (change in contract cost and scope). Various types of research investigated cost deviation or contract cost change by identifying the most critical factors or developing forecast models for them [ [6] , [7] , [8] , [9] , [10] , [11] , [12] , [13] , [14] , [15] , [16] ].…”

Inteligência artificial para automação de estimativa de custo em projeto arqitetônico

“…Logo, espera-se que o levantamento de parâmetros, bem como sua respectiva categorização, facilite o processo de escolha dos insumos alimentadores de máquina. Miranda et al (2022) explicam que ao seguir métodos de identificação de parâmetros mais rígidos, usando melhores dados e tomando as devidas considerações de poder preditivo, os modelos produzem previsões mais confiáveis. Lian, Wang e Hu (2022) experimentaram a criação de um problema com ANN.…”