Human Resource Selection Based on Performance Classification Using Weighted Support Vector Machine

Recruitment and selection have the first priority in human resource management. Traditional methods is based on linear model, it selects candidate by appraisal and ranking. However, selection system is intricate and nonlinear. Ranking method can not find the right person sometimes. For a ranked candidate, the job performance after being selected is unclear. The recruitment is unsuccessful when the candidate can not perform the expected job performance. In order to find the right person for the right position, this paper proposes a selection system using support vector machine (SVM). This system is fit for the nonlinear problem, and it gives a prediction of job performance. Considering the character of human resource selection problem, a weighted method based on weighted support vector machine (WSVM) is proposed. This method can improve the performance of traditional SVM. Technique of scaling, expert judgment, simple additive weighted, analytic hierarchy process (AHP) and questionnaire survey were used in this study. Simulation results show that classification system based on SVM is valid for human resource selection; furthermore, WSVM performs a better efficiency than traditional SVM for job performance classification. This proposed system can be used to support the decision of human resource selection.