Paper Details: Downloads: 514
Serial Number: P1121133727
Title: Knowledge Discovery from Support Vector Machines with Application to Credit Screening
Authors: Yan-Cheng Chen and Chao-Ton Su
Abstract: Support vector machines (SVMs) are state-of–the-art tools used to address issues pertinent to classification. The explanation capabilities of SVMs are also their main weakness, which is why SVMs are typically regarded as incomprehensible black box models. We propose a rule extraction algorithm from SVMs, in which a kernel-based clustering algorithm approach integrates all support vectors and genetic algorithms into the extracted rule sets. Measurements of accuracy and comprehensibility were utilized to evaluate the performance of our proposed method on the credit screening data sets. Finally, the results indicated the practicality of the proposed method on the credit screening data sets.
Keywords: Rule extraction, Support vector machines, Genetic algorithms, Credit screening.
Journal/Conference: ICGST Conference on Computer Science and Engineering, CSE-11
Volume:
Issue:
Submission Date: 8/15/2011 12:00:00 AM
Review Date: 10/2/2011 12:00:00 AM
Publishing Date: 12/19/2011 12:00:00 AM
Article Downloads: 514
Download:

Facebook