Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment
Credit risk has been one of the major challenges emerged from the banking industry in modern financial markets. Served as a typical method, association classification (AC) has been widely used for personal credit risk assessment. It focuses on the relationship between an item and a class based on mi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2019-12-01
|
Series: | Systems Science & Control Engineering |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/21642583.2019.1694597 |
id |
doaj-d2316f56a05d4dda8e18fb6e51cb351e |
---|---|
record_format |
Article |
spelling |
doaj-d2316f56a05d4dda8e18fb6e51cb351e2020-11-25T01:22:59ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832019-12-017313514210.1080/21642583.2019.16945971694597Hybridizing association rules with adaptive weighted decision fusion for personal credit assessmentYue Zhang0Quansheng Huang1Kai Zhao2Anhui Polytechnic UniversityAnhui Polytechnic UniversityAnhui Polytechnic UniversityCredit risk has been one of the major challenges emerged from the banking industry in modern financial markets. Served as a typical method, association classification (AC) has been widely used for personal credit risk assessment. It focuses on the relationship between an item and a class based on mined association rules, where three measures, i.e. support, confidence and weighted Chi-square, are generally used to generate association rules. However, most of the existing approaches neglect the discrimination power differences from between items, between measures and between rules. To deal with this problem, in this paper we present a novel approach characterized by hybridizing association rules with adaptive weighted decision fusion (HAR-AWDF) for personal credit assessment. Here in measures and rules are all worked as classifiers, and adaptive weightings are assigned to items via information entropies computed by posterior probabilities of individual items, also to measures and rules with their classification performance. In particular, a threshold scheme is proposed to determine whether a rule is effective, thereby the final decision is made via weighted voting in classification. The experimental results obtained conducting our approach on German Credit Data set show that among all items of the applied credit data, property, savings account and credit history are vital to evaluate personal credit state, in terms of classification accuracy.http://dx.doi.org/10.1080/21642583.2019.1694597personal credit assessmentassociation classificationinformation entropyadaptive weightingweighted votingdecision fusion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yue Zhang Quansheng Huang Kai Zhao |
spellingShingle |
Yue Zhang Quansheng Huang Kai Zhao Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment Systems Science & Control Engineering personal credit assessment association classification information entropy adaptive weighting weighted voting decision fusion |
author_facet |
Yue Zhang Quansheng Huang Kai Zhao |
author_sort |
Yue Zhang |
title |
Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment |
title_short |
Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment |
title_full |
Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment |
title_fullStr |
Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment |
title_full_unstemmed |
Hybridizing association rules with adaptive weighted decision fusion for personal credit assessment |
title_sort |
hybridizing association rules with adaptive weighted decision fusion for personal credit assessment |
publisher |
Taylor & Francis Group |
series |
Systems Science & Control Engineering |
issn |
2164-2583 |
publishDate |
2019-12-01 |
description |
Credit risk has been one of the major challenges emerged from the banking industry in modern financial markets. Served as a typical method, association classification (AC) has been widely used for personal credit risk assessment. It focuses on the relationship between an item and a class based on mined association rules, where three measures, i.e. support, confidence and weighted Chi-square, are generally used to generate association rules. However, most of the existing approaches neglect the discrimination power differences from between items, between measures and between rules. To deal with this problem, in this paper we present a novel approach characterized by hybridizing association rules with adaptive weighted decision fusion (HAR-AWDF) for personal credit assessment. Here in measures and rules are all worked as classifiers, and adaptive weightings are assigned to items via information entropies computed by posterior probabilities of individual items, also to measures and rules with their classification performance. In particular, a threshold scheme is proposed to determine whether a rule is effective, thereby the final decision is made via weighted voting in classification. The experimental results obtained conducting our approach on German Credit Data set show that among all items of the applied credit data, property, savings account and credit history are vital to evaluate personal credit state, in terms of classification accuracy. |
topic |
personal credit assessment association classification information entropy adaptive weighting weighted voting decision fusion |
url |
http://dx.doi.org/10.1080/21642583.2019.1694597 |
work_keys_str_mv |
AT yuezhang hybridizingassociationruleswithadaptiveweighteddecisionfusionforpersonalcreditassessment AT quanshenghuang hybridizingassociationruleswithadaptiveweighteddecisionfusionforpersonalcreditassessment AT kaizhao hybridizingassociationruleswithadaptiveweighteddecisionfusionforpersonalcreditassessment |
_version_ |
1725124216018173952 |