The type and number of defects constitute a major indicator of project quality and are thus emphasized in project management. Therefore, it is necessary to explore appropriate tools and methods to train/test/analyze defect-related big data in order to effectively explain the cause/rule/importance of the defect, to understand the focus of site management, and to effectively prevent defects. The aim of this study is to explore the capability of three kinds of decision tree algorithms, namely classification and regression tree (CART), chi-squared automatic interaction detection (CHAID) and quick unbiased efficient statistical tree algorithms (QUEST), in predicting the construction project grade given defects. Firstly, a total of 499 types of defects were identified after the analysis of the data of 990 projects obtained from the Public Construction Management Information System (PCMIS). Secondly, inspection scores and defect frequencies were estimated to perform cluster analysis for re-grouping the data to create project grade. Thirdly, decision trees were used to classify rules for defects and project grades. The results revealed that, among the three algorithms, CHAID generated the most classification rules and exhibited the highest defect prediction accuracy. The finding of this research can improve the defect prediction accuracy and management effectiveness for construction industry.
29 June 2018 in JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT
This paper explores the relations between defect types and quality inspection grades of public construction projects in Taiwan. Altogether, 499 defect types (classified from 17,648 defects) were found after analyzing 990 construction projects from the Public Construction Management Information System of the public construction commission which is a government unit that administers all the public construction. The core of this research includes the following steps. (1) Data mining (DM) was used to derive 57 association rules which altogether contain 30 of the 499 defect types. (2) K-means clustering was used to regroup the 990 projects of two attributes (defect frequency and original grading score of each project) into four new quality classes, so the 990 projects can be more evenly distributed in the four new classes and the correctness and reliability of the following analyses can be ensured. (3) Finally analysis of variance (ANOVA), fuzzy logic, and correlation analysis were used to verify that the aforementioned 30 defect types are the important ones determining inspection grades. Results of this research can help stakeholders of construction projects paying more attention on the root causes of the critical defect types so to dramatically raise their management effectiveness.