Diversity of Feature Selection Approaches Combined with Back-Propagation Neural Network in Credit Scoring
MetadataShow full item record
The credit scoring has been regarded as a critical topic and its related departments make efforts to collect huge amount of data to avoid wrong decision. An effective classificatory model will objectively help managers instead of intuitive experience. This study proposes five approaches combining with the backpropagation neural network (BPN) classifier for features selection that retains sufficient information for classification purpose. Different credit scoring models are constructed by selecting attributes with five approaches. Two UCI (University of California, Irvine) data sets are chosen to evaluate the accuracy of various hybrid-BPN models. BPN classifier combines with conventional statistical LDA, Decision tree, Rough sets theory, F-score and Gray relation approaches as features preprocessing step to optimize feature space by removing both irrelevant and redundant features. In this paper, the procedure of the proposed approaches will be described and then evaluated by their performances. The results are compared in combination with BPN classifier and nonparametric Wilcoxon signed rank test will be held to show if there is any significant difference between these models. The result in this study suggests that hybrid credit scoring approach is mostly robust and effective in finding optimal subsets and is a promising method to the fields of data mining.
Showing items related by title, author, creator and subject.
Chikolwa, Bwembya C (2008)According to the Reserve Bank of Australia (2006) the increased supply of Commercial Mortgage-Backed Securities (CMBS), with a range of subordination, has broadened the investor base in real estate debt markets and reduced ...
An exploration of the global development of emerging country multinationals : a study of strategic ambitions and talent management in China and IndiaLiu, Yi (2012)Since Jim O’Neill, the Goldman Sachs economist, coined the acronym of the BRIC countries in 2001 the concept has attracted an infectious logic. The growth of the four BRIC countries, Brazil, Russia, India, and China, is ...
The impact of instructional interventions on students' learning approaches, attitudes, and achievement.Edwards, Peta S. (1999)Many interacting factors need to be considered when contemplating the optimum conditions for the creation of a learning environment that is compatible with the aims of tertiary teaching and learning. In the current economic ...