Credit assessment with random forests

Abstract

Because the credit industry has a lot of bad debt problems, credit assessment has become a very important topic in financial institutions. Recent studies have shown that many algorithms in the fields of machine learning and artificial intelligence are competitive to statistical methods for credit assessment. Random forests, one of the most popular ensemble learning techniques, is introduced to the credit assessment problem in this paper. An experimental evaluation of different methods is carried out on the public dataset. The experimental results indicate that the random forests method improves the performance obviously. © 2011 Springer-Verlag.