Using data mining in the selection process of high performance managers

The selection of high performance managers involves a significant level of subjectivity. Aiming at reducing this subjectivity and mitigating possible losses, many approaches have been proposed to select the candidates that best fit into a given position. However, defining what are the most important features for a good personnel performance is still a problem. This paper details the ideas and results presented in two previous works that describe an approach, based on data mining techniques, to help managers in this process. A classifier, built over the combinatorial neural model (CNM), is described that takes as dependent variable the performance of managers as observed along their careers. As independent variables, we considered the results of well-known psychological tests (MBTI and DISC). The rules generated correlate psychological profiles of novice managers and the quality of their work after some years. These results enable a better management of people selection and allocation.