Font Size: 

A series of challenges have recently emerged in the data mining field, triggered by the rapid shift in status from academic to applied science and the resulting needs of real-life applications. The recourse to statistical learning models as support vector machines (SVM), or neural networks, is a common practice. However, the performances of those algorithms strongly depend on the quality of the data used. This constraint, oblige the data scientist to employ different statistical methods before using those algorithms. This paper aims to apply feature selection method on financial data of 20 firms in order to to set up our Support Vector Machine (SVM) Model through which we can predict firms’ creditworthiness risk