Decision Support Model for Employee Recruitment Using Data Mining Classification

Abstract

This article explains a decision support model (DSM) construction for employee recruitment in a particular IT consultant company using the conception of data mining classification. The created model addresses the company’s need in recruiting employees objectively by utilizing historical data to find patterns of potential employees for the company. There are four data mining classification algorithms compared in this case, namely C4.5 Decision Tree, Naive Bayes, Support Vector Machine, and Random Forest. The algorithm with the highest accuracy, specificity, and sensitivity values are operated to produce rules for the DSM. The results are C4.5 Decision Tree has the highest accuracy of 88.24%, specificity of 88.10% and sensitivity of 100%;thus this algorithm is selected to process the value of eight predictor parameter to propose the most valuable employee candidate.