4129-4145 a comparative analysis of machine learning techniques for credit scoring

Nnamdi I. Nwulu, Shola Oroja, Mustafa Ilkan

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

Credit Scoring has become an oft researched topic in light of the increasing volatility of the global economy and the recent world financial crisis. Amidst the many methods used for credit scoring, machine learning techniques are becoming increasingly popular due to their efficient and accurate nature and relative simplicity. Furthermore machine learning techniques minimize the risk of human bias and error and maximize speed as they are able to perform computationally difficult tasks in very short times. In this work, a comparative analysis is performed between two machine learning techniques namely Support Vector Machines and Artificial Neural Networks. This study compares both techniques in terms of accuracy, computational complexity and processing times. In order to assure meaningful comparisons, a real world dalaset precisely the Australian Credit Scoring data set is used for this task. Obtained experimental results show that although both machine learning techniques can be applied successfully, Artificial Neural Networks slightly outperform Support Vector Machines.

Original languageEnglish
Pages (from-to)4129-4145
Number of pages17
JournalInformation
Volume15
Issue number10
Publication statusPublished - Oct 2012
Externally publishedYes

Keywords

  • Artificial neural networks
  • Credit scoring
  • Machine learning
  • Support vector machines

ASJC Scopus subject areas

  • Information Systems

Fingerprint

Dive into the research topics of '4129-4145 a comparative analysis of machine learning techniques for credit scoring'. Together they form a unique fingerprint.

Cite this