Title: Selecting useful features for personal credit risk analysis

Authors: Li Shukai, Narendra S. Chaudhari, Manoranjan Dash

Addresses: School of Computer Engineering, Centre for Computational Intelligence, Nanyang Technological University, Blk. N4, #B1a-02, Nanyang Avenue, 639798, Singapore. ' School of Computer Engineering, Centre for Computational Intelligence, Nanyang Technological University, Blk. N4, #B1a-02, Nanyang Avenue, 639798, Singapore. ' School of Computer Engineering, Centre for Computational Intelligence, Nanyang Technological University, Blk. N4, #B1a-02, Nanyang Avenue, 639798, Singapore

Abstract: The recent credit crisis has renewed regulatory concerns of industrial interest in credit risk analysis. To reduce exposure to credit default, it thus becomes a crucial motive to select vital features to analyse the customer|s credit profiles. This desired set of features can be generated through data mining techniques such as feature selection methods. However, each feature selection method has its advantages and limitations. In practice, using a single method inevitably introduces undesirable estimation bias. Instead, this paper proposes a bagging feature selection model, which is an ensemble learning approach, to identify the most significant features that determine the credit worthiness of customers. The experimental results demonstrate promising results using bagging feature selection model as compared to fundamental models for personal credit risk analysis.

Keywords: feature selection; ensemble learning; personal credit; risk analysis; credit crisis; regulation; credit default; customer profiles; data mining; estimation bias; bagging features; credit worthiness; Germany; business information systems; risk assessment.

DOI: 10.1504/IJBIS.2010.035745

International Journal of Business Information Systems, 2010 Vol.6 No.4, pp.530 - 546

Published online: 03 Oct 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article