Comparison of criteria for the selection of discriminating variables: Application in Credit-Scoring

Journal Title: Scholars Journal of Physics, Mathematics and Statistics - Year 2015, Vol 2, Issue 2

Abstract

Banks want to reduce the credential risk by applying rules in order to classify the new loan seekers into “good customers” and “bad customers”. Searching past data is the best solution to build a statistics strategy to show this kind of risk. In general, a lot of data should be analyzed using “Data Mining”, the computational process of discovering patterns in large data sets involving methods, formalizing the problem of credential risk that the bank is seeking to resolve in terms of data (classification tree), while the dependent variable is qualitative and takes two forms: "good payers" and "defaulters". From that, prepare the data for treatment (selection of the most discriminating variables, collinearity diagnosis). Finally model the data by logistic regression and the decision tree CART. This article aims to build these two classification models from a database of 1000 customers by using first the chi-square criteria χ2 and secondly Rand as a detector of discriminating variables in order to choose the most appropriate criterion.

Authors and Affiliations

Hicham Y. Abdallah, Afif A. Hayek

Keywords

Related Articles

An integrated and logistic approach to surface transport model: Some results for Odisha

The author’s intention in present article is to focus properly the impact of some socio-economic indicators like agriculture, forestry, industry, mining, storage, fisheries, electricity, hotel, communication, real estate...

A Class of Reflected BSDE with Integrable Parameters

In this paper, we establish an existence and uniqueness result for solutions to one dimensional reflected backward stochastic differential equations (RBSDEs) with only integrable parameters, where the generator is -Ho...

A Numerical Solution for Fractional Damped Mechanical Oscillator Equation

In this article, we have investigated the numerical approach for solving the fractional damped mechanical oscillator equation, which has an important role in fractional calculus. Damped mechanical oscillator equation equ...

Secondary Critical Path in a Fuzzy Project Network

In a fuzzy project network, the higher risk path is called possible critical path. Secondary critical path is one of the possible critical path in fuzzy project network and it plays an important role in the project sche...

The minimum group congruence on a GV-semi group

A GV-semi group is a semi group in which some power of each element is regular and every regular element lies in a subgroup. The minimum group congruence on a GV-semi group is investigated by means of establishing a subs...

Download PDF file
  • EP ID EP384534
  • DOI -
  • Views 111
  • Downloads 0

How To Cite

Hicham Y. Abdallah, Afif A. Hayek (2015). Comparison of criteria for the selection of discriminating variables: Application in Credit-Scoring. Scholars Journal of Physics, Mathematics and Statistics, 2(2), 176-190. https://europub.co.uk/articles/-A-384534