Hybrid mining approach in the design of credit scoring models Export

@article{2005_Hsieh, abstract = {Unrepresentative data samples are likely to reduce the utility of data classifiers in practical application. This study presents a hybrid mining approach in the design of an effective credit scoring model, based on clustering and neural network techniques. We used clustering techniques to preprocess the input samples with the objective of indicating unrepresentative samples into isolated and inconsistent clusters, and used neural networks to construct the credit scoring model. The clustering stage involved a class-wise classification process. A self-organizing map clustering algorithm was used to automatically determine the number of clusters and the starting points of each cluster. Then, the K-means clustering algorithm was used to generate clusters of samples belonging to new classes and eliminate the unrepresentative samples from each class. In the neural network stage, samples with new class labels were used in the design of the credit scoring model. The proposed method demonstrates by two real world credit data sets that the hybrid mining approach can be used to build effective credit scoring models. (c) 2005 Elsevier Ltd. All rights reserved.}, author = {Hsieh, N. C.}, citeulike-article-id = {651353}, journal = {Expert Systems with Applications}, keywords = {class-wise, classification, clustering, consumer, credit, data-mining, k-means, market-segmentation, neural-networks, performance, scoring}, number = {4}, pages = {655--665}, posted-at = {2006-05-18 18:20:37}, priority = {0}, title = {Hybrid mining approach in the design of credit scoring models}, volume = {28}, year = {2005} }

TY - JOUR ID - 2005_Hsieh L3 - citeulike-article-id:651353 N2 - Unrepresentative data samples are likely to reduce the utility of data classifiers in practical application. This study presents a hybrid mining approach in the design of an effective credit scoring model, based on clustering and neural network techniques. We used clustering techniques to preprocess the input samples with the objective of indicating unrepresentative samples into isolated and inconsistent clusters, and used neural networks to construct the credit scoring model. The clustering stage involved a class-wise classification process. A self-organizing map clustering algorithm was used to automatically determine the number of clusters and the starting points of each cluster. Then, the K-means clustering algorithm was used to generate clusters of samples belonging to new classes and eliminate the unrepresentative samples from each class. In the neural network stage, samples with new class labels were used in the design of the credit scoring model. The proposed method demonstrates by two real world credit data sets that the hybrid mining approach can be used to build effective credit scoring models. (c) 2005 Elsevier Ltd. All rights reserved. IS - 4 JF - Expert Systems with Applications EP - 665 TI - Hybrid mining approach in the design of credit scoring models VL - 28 SP - 655 KW - class-wise KW - classification KW - clustering KW - consumer KW - credit KW - data-mining KW - k-means KW - market-segmentation KW - neural-networks KW - performance KW - scoring AU - Hsieh, NC PY - 2005/// ER -