Rethinking construction cost overruns: cognition, learning and estimation

TLDR

Cost overruns in construction projects are driven by cognitive dispositions, learning deficits, and estimation errors, as argued in mainstream literature. The study aims to discuss and clarify the causes of cost overruns and the interplay of cognition, learning, and estimation. The authors used a mixed‑method design, combining qualitative exploration of cost‑overrun causes with an empirical neural‑network model to predict final project cost. The study produced a conceptual model separating underestimation from cost overruns and an empirical neural‑network cost‑prediction model achieving a 3.67 % average absolute error, with 87 % of predictions within ±5 %, offering a ready‑to‑use desktop tool that can streamline estimation and reduce resource use.

Abstract

Purpose – Drawing on mainstream arguments in the literature, the paper presents a coherent and holistic view on the causes of cost overruns, and the dynamics between cognitive dispositions, learning and estimation. A cost prediction model has also been developed using data mining for estimating final cost of projects. The paper aims to discuss these issues. Design/methodology/approach – A mixed-method approach was adopted: a qualitative exploration of the causes of cost overrun followed by an empirical development of a final cost model using artificial neural networks. Findings – A conceptual model to distinguish between the often conflated causes of underestimation and cost overruns on large publicly funded projects. The empirical model developed in this paper achieved an average absolute percentage error of 3.67 percent with 87 percent of the model predictions within a range of ±5 percent of the actual final cost. Practical implications – The model developed can be converted to a desktop package for quick cost predictions and the generation of various alternative solutions for a construction project in a sort of what-if analysis for the purposes of comparison. The use of the model could also greatly reduce the time and resources spent on estimation. Originality/value – A thorough discussion on the dynamics between cognitive dispositions, learning and cost estimation has been presented. It also presents a conceptual model for understanding two often conflated issues of cost overrun and under-estimation.