Today, the choice of featured managers is a very important issue in government agencies. People who have managerial competencies are those that have several characteristics which are mentioned in this article and on the basis of these parameters, it is predicted which individuals have management qualifications. In this paper, employees of several organizations in one of the cities of the country has been studied and it is specified which persons have managerial qualifications. Since those people have a high ability ranking, usually are minority in class, but those who do not have such qualification, are majority in class. This dataset has an imbalanced property. In this paper, the proposed algorithm is a combination of SMOTE algorithm, Imperialist Competitive Algorithm (ICA) and the decision tree. And also to calculate the performance of proposed method, some assessments such as Accuracy, GMean, Specificity, Sensitivity, has been used. The results show that combining the SMOTE & ICA & C5 algorithms would have the best result in imbalanced data classification and in prediction of these kind of data.