Feature Selection for Construction Organizational Competencies Impacting Performance

Organizational competencies have a significant influence on performance; therefore, it is vital that organizations in the construction industry assess and enhance their competencies in order to improve performance. The set of variables that captures construction organizational competencies is highly dimensional. Feature selection (FS) helps to reduce the dimensionality of data by using only a subset of variables to develop a model. The main objective of the research presented in this paper is the development of a fuzzy inference system (FIS) applying fuzzy c-means clustering (FCM) and FS using genetic algorithms (GAs). First, the parameters of FCM are optimized and used to develop an FIS. Then, the FIS is optimized using a GA. The root mean square error (RMSE) is used as a fitness function for GA optimization. This paper contributes an FS approach for construction engineering and management problems that are characterized by high dimensionality of feature space and few data instances.