Computer-Aided Civil and Infrastructure Engineering 30 (2015) 120–134 A Grey System Theory-Based Default Prediction Model for Construction Firms Hui Ping Tserng* Department of Civil Engineering, National Taiwan University, Taipei, Taiwan Thanh Long Ngo Department of Civil Engineering, National Taiwan University, Taipei, Taiwan and Department of Construction Mechanical Engineering, National University of Civil Engineering, Hanoi, Vietnam Po Cheng Chen & Le Quyen Tran Department of Civil Engineering, National Taiwan University, Taipei, Taiwan Abstract: As the prediction of construction firm failure is of great importance for owners, contractors, investors, banks, insurance firms, and creditors, previous studies have developed several models for predicting the prob- ability of construction firm default based on financial ra- tio analysis. However, to be applied, these models require a considerable quantity of data, including normally dis- tributed data, and the models cannot tolerate too many changing factors. Furthermore, most of the approaches produce sample selection biases. To avoid these disad- vantages, this study is the first to integrate the grey sys- tem theory with all available firm-year samples during the sample period to provide a new method for predicting the probability of construction firm default. This method not only offers an improved rate of prediction accuracy, but it also offers simpler and clearer procedures as a ref- erence for examining firm default probability and ranks all financial ratios in terms of their level of importance. The research collects and analyzes the financial reports of 92 construction firms in the United States. The pro- posed model includes only eight ranked variables (finan- cial ratios), and it achieves an 84.8% level of accuracy for predicting construction firm default probability. As a re- sult, practitioners may directly use the model as a means of quickly and conveniently examining their firm default probability with the simple procedures. ∗ To whom correspondence should be addressed. E-mail: hptserng@ ntu.edu.tw. 1 INTRODUCTION Because predicting the probability of default for a com- pany has been an important research topic in finance, accounting, and auditing for the last three decades (Lin, 2009; Wu et al., 2007; Salcedo-Sanz et al., 2005; Tserng et al., 2011a), it has attracted many leading researchers. Although there were many studies of company default prediction models, the focus of these studies had been limited to the nonconstruction industries. Chava and Jarrow (2004) stated that different industries have dif- ferent accounting conventions and different levels of competition; therefore, the probability of default may differ for companies in different industries with other- wise identical balance sheets. Many scholars, such as Tserng et al. (2011a, 2011b), Chen (2012), Chen (2009), Kangari et al. (1992), Lee et al. (2011), Wang et al. (2008), and Cruz and Marques (2012) have shown that the special characteristics and financial risks of the con- struction industry are significantly different from other industries in many ways. First, construction firms face a high degree of uncertainty and high operational risks, due to technical, human, and natural factors. Second, as the construction industry is a project-based indus- try, projects dominate most firms’ operations. Third, because construction firms deal with large projects, their values may include total firm assets. As a result, the capital structures of these firms are quite different from other types of industries. Fourth, the construction industry is easily influenced by the current economic situation. Fifth, as inventory cannot be realized into C  2014 Computer-Aided Civil and Infrastructure Engineering. DOI: 10.1111/mice.12074