Towards Automated Cost Analysis, Benchmarking and Estimating in Construction: A Machine Learning Approach

Abstract

In this paper, a novel machine learning based approach is proposed for automated cost analysis on priced bill of quantities prepared by tenders in the construction industry. The proposed approach features: 1) An effective integration of structured project-specific information with surveyor's domain knowledge in order to model the complex interrelationships between the specifications and descriptions of an item and its trade category; 2) An effective transformation by supervised t-SNE to map the original data into a 2-dimensional space to tackle issues of high dimensionality in modelling and creating classifiers, and 3) Simple classifiers with a high classification accuracy and a good generalization capability. Relevant comparative experimental results have demonstrated the effectiveness of the proposed approach.

An automated machine learning approach for classifying infrastructure cost data

“…Furthermore, the proposed novel approach for automated classification of infrastructure cost data into a consistent format outperformed previous attempts, such as Chen et al. (2019) and Martínez‐Rojas (2015).…”

“…For example, Chen et al. (2019) proposed the combination that encompasses the accountant surveyor's knowledge with five different binary classifiers for automated cost analysis of priced BOQs data by classifying cost items into their trade‐based categories.…”

“…But once again, the lack of consistency in cost reporting practices across the infrastructure construction supply chain and client organizations presents a huge challenge for the mining of cost information in consistent formats and structures that enable robust comparison of like‐for‐like during benchmarking (Chen et al., 2019).…”

“…As a result of these contextual differences, some cost breakdown structures are based on construction trades, and asset types, while some are based on construction elements or activities (Chen et al., 2019). Even where two organizations use the same “standards,” there can still be discrepancies in the way individual projects or professionals present the data.…”

Predicting construction project compliance with machine learning model: case study using Portuguese procurement data

“…Construction applications are detailed and complex documents compiled according to different assumptions given a specific project (Poças Martins and Abrantes Almeida, 2009), traditionally, it has been challenging to accurately predict budget compliance (Jafari et al, 2021;Elhegazy et al, 2021). The emergence of Artificial Intelligence may change this paradigm; however, due to technical and cultural reasons, these technologies, which have already been implemented in similar industries, have only started to be adopted by the construction sector (Chen et al, 2019). In recent years, different Machine Learning (ML) algorithm architectures have been adopted in various stages of the construction process (Jacques de Sousa et al, 2023b).…”