Analysis of Causality between Defect Causes Using Association Rule Mining

Authors: Sangdeok Lee, Sangwon Han, Changtaek Hyun

Abstract:

Construction defects are major components that result in negative impacts on project performance including schedule delays and cost overruns. Since construction defects generally occur when a few associated causes combine, a thorough understanding of defect causality is required in order to more systematically prevent construction defects. To address this issue, this paper uses association rule mining (ARM) to quantify the causality between defect causes, and social network analysis (SNA) to find indirect causality among them. The suggested approach is validated with 350 defect instances from concrete works in 32 projects in Korea. The results show that the interrelationships revealed by the approach reflect the characteristics of the concrete task and the important causes that should be prevented.

Keywords: Causality, defect causes, social network analysis, association rule mining.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1125579

References:

[1] Josephson, P., and Hammarlund, Y. (1999), “The Causes and Costs of Defects in Construction: A Study of Seven Building Projects”, Automation in Construction, 8(6), 681-687.
[2] Mills, A., Love, P., and Williams, P. (2009), “Defect Costs in Residential Construction”, Journal of Construction Engineering and Management, 135(1), 12-46.
[3] Love, P., Edwards, D., Irani, Z., and Walker, D. (2009), “Project Pathogens: The Anatomy of Omission Errors in Construction and Resource Engineering Project”, Engineering Management, IEEE Transactions on, 56(3), 425-435.
[4] Aljassmi, H., and Han, S. (2013), “Analysis of Causes of Construction Defects Using Fault Trees and Risk Importance Measures”, Journal of Construction Engineering and Management, 139(7), 870-880.
[5] Cheng, Y., Yu, W., and Li, Q. (2015), “GA-based multi-level association rule mining approach for defect analysis in the construction industry”, Automation in Construction, 51, 78-91.
[6] Cui, J. (2011), “Analysis of Construction Quality Accident Causes of Public Buildings Based on Failure Study Theories”, Computer and Management (CAMAN), 2011 International Conference on. IEEE, 1-4.
[7] Abdul-Rahman, H., Al-Tmeemy, S., Harun, Z., and Ye, M. (2014), The major causes of quality failures in the Malaysian building construction industry.
[8] Chen, W., Tseng, S., and Wang, C. (2005), “A novel manufacturing defect detection method using association rule mining techniques”, Expert Systems with applications, 29(4), 807-815.
[9] Wang, Z., Hu, Xiong, and Chen, Z. (2007), “Mining Association Rules on Data of Crane Health-Condition Monitoring”, International Conference on Transportation Engineering 2007, ASCE, 2054-2059.
[10] Brijs, T., Vanhoof, K., and Wets, G. (2003), “Defining interestingness for association rules”, Institute of Information Theories and Applications FOI ITHEA, 10(4), 370-375.
[11] Aljassmi, H., Han, S., and Davis, S. (2014), “Project Pathogens Network: New Approach to Analyzing Construction-Defects-Generation Mechanisms”, Journal of Construction Engineering and Management, 140(1).
[12] Freeman, L. (1978), “Centrality in social networks conceptual clarification”, Social networks, 1(3), 215-239.
[13] Wasserman, S., and Faust, K. (1994), Social network analysis: Methods and applications, Cambridge university press.
[14] Borgatti, S., Everett, M., and Freeman, L. (2002), Ucinet for Windows: Software for Social Network Analysis, Harvard, MA: Analytic Technologies.