A three-group discrimination using new linear programming model

The applications that are related to classification problem are wide-ranging. In fact, differentiating between patients with strong prospects for recovery and those highly at risk, between good credit risks and poor ones, or between promising new firms and those likely to fail are among the most known of these applications. To solve such classification problem, several approaches have been applied, such as the parametric procedures and the non-parametric procedures. This paper aims at developing a new technique to resolve the three-group classification problems. This approach is based on the linear programming models. To evaluate the efficiency of our model, the three-group classification problems were compared with two other traditional classification methods, namely, linear discriminant analysis and classification tree. The results obtained are found to be satisfactory. The performance of the new approach, a parametric statistical technique and a non-parametric method is then evaluated on a data set.