Knowledge Representation and Discovery Using Formal Concept Analysis: An HRM Application

Abstract

Knowledge discovery process from databases has gained importance recently. Finding and using the valuable and meaningful data which is hidden in large databases can have strategic importance for the organizations to gain competitive advantage. Knowledge discovery process that is based on data mining consists of two methods named symbolic and numeric. The symbolic methods based on formal concept analysis classification are frequent itemset search and association rule extraction. Concept lattices are the knowledge representation of formal concept analysis. Association rules based on lattice reflect the relationships among the attributes in a database. In this study, the mathematical background and definition of formal concept analysis which is a powerful tool in knowledge representation and discovery are explained. Then, an experimental study is given in employee recruitment function of human resources management by using formal concept analysis method to model the qualifications of candidates during the recruitment process by taking into consideration the essential qualifications needed for the job position. After that association rules and implications are obtained in order to facilitate the decision making process to select the appropriate candidate for the vacant position.