Dealing with construction cost overruns using data mining

Abstract

One of the main aims of any construction client is to procure a project within the limits of a predefined budget. However, most construction projects routinely to overrun their cost estimates. Existing theories on construction cost overrun suggest a number of causes ranging from technical difficulties, optimism bias, managerial incompetence and strategic misrepresentation. However, much of the budgetary decision making process in the early stages of a project is carried out in an environment of high uncertainty with little available information for accurate estimation. Using nonparametric bootstrapping and ensemble modelling in artificial neural networks, final project cost forecasting models were developed with 1600 completed projects in this experimental research. This helped to extract information embedded in data on completed construction projects, in an attempt to address the problem of dearth of information in the early stages of a project. 92% of the 100 validation predictions were within ±10% of the actual final cost of the project whiles 77% were within ±5% of actual final cost. This indicates the model's ability to generalise satisfactorily when validated with new data. The models are being deployed within the operations of the industry partner involved in this research to help increase the reliability and accuracy of initial cost estimates.

Talking About Futureproofing: Real Options Reasoning in Complex Infrastructure Projects

“…Our study offers four broad theoretical implications related to ROR. First, prior to our study, there have been few attempts to formulate perspectives that allow the simultaneous study of multiple causes of an inadequate development process [19], [28], [62]. In addition, few studies have shown that decision-makers apply the logic of real options in project settings [4], [16], [43].…”

Veri Madenciliği Uygulamalarının ve Sezgisel Optimizasyon Algoritmalarının Yapım Yönetimindeki Yeri

“…Ahiaga-Dagbui ve Smith çalışmalarında [24], bir projenin ilk aşamalarında bütçesel karar vermede az bilgi ile doğru tahmini gerçekleştirmek için yapay sinir ağlarında parametrik olmayan topluluk modellemesi kullanarak 1600 tamamlanmış projeden aldığı veri ile nihai proje maliyet tahmin modelleri geliştirmişlerdir. Çalışma sonucunda, 100 doğrulama öngörüsünün %92'sinin projenin fiili nihai maliyetinin ±%10'u dahilinde olduğu bulunurken, %77'sinin fiili nihai maliyetin ±%5'i dahilinde gerçekleştiği tespit edilmiştir.…”

Model of Predicting Cost Overrun in Construction Projects

“…These models are based on regression analysis and case based reasoning. Ahiaga-Dagbui and Smith [22] made a case for using data mining in modern construction management as a key business tool to help transform information embedded in the construction data into decision support systems that can complement traditional estimation methods for more reliable final cost forecasting. Using a combination of non-parametric bootstrapping and ensemble modelling in artificial neural networks, cost models were developed to estimate the final construction cost of water infrastructure projects.…”