A Comparative Analysis of Machine Learning Techniques for Credit Scoring

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 dataset 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.