Soft computing methods for personnel selection based on the valuation of competences

Autores UPV


Personnel selection based on candidates¿ competences is a difficult task due to the imprecise description of the applicants¿ competences and to the existence of several experts simultaneously evaluating those attributes. In this context, fuzzy sets theory provides suitable tools for the attainment of the maximum possible information from imprecise data. In this work, personnel selection methods are proposed that rely on the definition of an ideal candidate. Aggregated fuzzy valuations of each candidate are obtained taking into account the individual valuations provided by the experts. Then, candidates are ranked based on their similarity with the ideal candidate. Three different scenarios are considered: the ideal candidate is explicitly known, the ideal candidate is implicitly known, or the ideal candidate cannot be defined by the firm. In the first case, similarity or inclusion indexes are used; in the second, the use of ordered weighted average operators allows us to simulate global valuations for the candidates. Finally, if there is not an ideal profile, it can be constructed from the competences¿ valuations of the candidates. To illustrate the proposed methods, a real personnel selection example is presented and solved using a program called StaffDesigner, especially designed for this work.