Developing a recommender system for assigning projects to supervising engineers (Case study: Damghan construction engineering organization)

10.52547/jde.2.7.71
Abstract
Supervising engineers are one of the most important actors in construction industry and have an important role in improving quality and increasing safety. However, assigning projects to these engineers in some cases are unjust and inefficient. Therefore, in this paper a recommender system is developed in which the competencies of engineers along with the features of the projects are considered. This is done in three phases: in the first phase, the key competencies are defined. The engineers are then classified into two classes and ranked in each class. In the second phase, the projects are evaluated and ranked based on the key features selected from the national and international standards. Finally, in the third phase, the projects are assigned to the respective engineers. In order to implement the developed system, Damghan construction engineering organization is selected and the obtained results are evaluated using an expert pannels. The results show that the recommendations are done accurately in about 87% cases.
Keywords
Recommander system
classification
Data envelopement analysis
Simple additive weighting
construction engineering organization
-Hardison, D., Behm, M., Hallowell, M. R., & Fonooni, H. (2014). Identifying construction supervisor competencies for effective site safety. Safety science, 65, 45-53.
-Ahn, Y.H., Kwon, H., Pearce, A.R., & Shin, H. (2010). Key competencies for US construction graduates: an exploratory factor analysis. In ASC Proceedings of the 46th Annual International Conference, Boston, MA.
-Ling, Y.Y., & Tan, F. (2015). Selection of site supervisors to optimize construction project outcomes. Structural Survey, construction project outcomes, 33, 407-422.
-Australian government, engineersaustralia org. (2016), Engineers Australia’s stage 1 and 2 professional standards.
-Jain, A.K. (2010). Data clustering 50 years beyond K-means. Pattern recognition letters, 31(8), 651-666.
-Employment and Training Administration (ETA). United States Department of Labor, (January 2015). Engineering Competency Model. http://www.doleta.gov
-Handl, J., Knowles, J. (2006). Multi-objective clustering and cluster validation Multi-Objective Machine Learning, Springer, pp. 21-47.