Construction of a k-nearest-neighbour credit-scoring system

by: WE Henley, Hand

IMA J Management Math, Vol. 8, No. 4. (1 October 1997), pp. 305-321.

View FullText article

DOI, HighWire

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

zlex

Find related articles with these CiteULike tags

creditscoring

Abstract

This paper describes the construction of a credit-scoring system using the k-nearest-neighbour method, a standard technique in pattern recognition and non-parametric statistics. An important part of our analysis is the selection of distance metrics. We propose using an adjusted version of the euclidean distance metric, which incorporates an estimate of underlying equiprobability contours for class membership. This approach was used to classify a sample of applications for mail-order credit from the Littlewoods Organisation. We describe the results of comparison experiments with a range of discrimination techniques, including logistic regression, projection-pursuit regression, and decision trees. 10.1093/imaman/8.4.305

@article{citeulike:2804645, abstract = {This paper describes the construction of a credit-scoring system using the k-nearest-neighbour method, a standard technique in pattern recognition and non-parametric statistics. An important part of our analysis is the selection of distance metrics. We propose using an adjusted version of the euclidean distance metric, which incorporates an estimate of underlying equiprobability contours for class membership. This approach was used to classify a sample of applications for mail-order credit from the Littlewoods Organisation. We describe the results of comparison experiments with a range of discrimination techniques, including logistic regression, projection-pursuit regression, and decision trees. 10.1093/imaman/8.4.305}, author = {Henley, W. E. and Hand}, citeulike-article-id = {2804645}, doi = {10.1093/imaman/8.4.305}, journal = {IMA J Management Math}, keywords = {creditscoring}, month = {October}, number = {4}, pages = {305--321}, posted-at = {2008-05-16 09:08:19}, priority = {2}, title = {Construction of a k-nearest-neighbour credit-scoring system}, url = {http://dx.doi.org/10.1093/imaman/8.4.305}, volume = {8}, year = {1997} }

RIS record

TY - JOUR ID - citeulike:2804645 L3 - citeulike-article-id:2804645 TI - Construction of a k-nearest-neighbour credit-scoring system JF - IMA J Management Math VL - 8 IS - 4 SP - 305 EP - 321 N2 - This paper describes the construction of a credit-scoring system using the k-nearest-neighbour method, a standard technique in pattern recognition and non-parametric statistics. An important part of our analysis is the selection of distance metrics. We propose using an adjusted version of the euclidean distance metric, which incorporates an estimate of underlying equiprobability contours for class membership. This approach was used to classify a sample of applications for mail-order credit from the Littlewoods Organisation. We describe the results of comparison experiments with a range of discrimination techniques, including logistic regression, projection-pursuit regression, and decision trees. 10.1093/imaman/8.4.305 KW - creditscoring AU - Henley, WE AU - Hand PY - 1997/10/01/ UR - http://dx.doi.org/10.1093/imaman/8.4.305 ER -

RIS BibTeX