MLP AND DEFAULT ARTMAP NEURAL NETWORKS FOR BUSINESS CLASSIFICATION

被引：0

作者：

Nachev, Anatoli ^{[1
]}

Stoyanov, Borislav ^{[1
]}

机构：

[1] Natl Univ Ireland, Cairnes Sch Business & Econ, Galway, Ireland

来源：

INTELLIGENT DECISION MAKING SYSTEMS, VOL. 2 | 2010年

关键词：

BANKRUPTCY PREDICTION;

D O I：

10.1142/9789814295062_0028

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

This study shows in an empirical form that a specific class of neural networks, Default ARTMAP, is superior to the most common MLP neural networks in predicting business insolvency Our experiments are based on data collected from 88 Irish firms over six years We experimented with different network parameters, variable selection, and daunt preprocessing Our results were verified and validated by several performance metrics, ROC analysis and leave-one-out cross-validation

引用

页码：179 / 184

页数：6

共 9 条

[1] FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND PREDICTION OF CORPORATE BANKRUPTCY
ALTMAN, EI
[J]. JOURNAL OF FINANCE, 1968, 23 (04) : 589 - 609
[2] Bankruptcy prediction for credit risk using neural networks: A survey and new results
Atiya, AF
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (04): : 929 - 935
[3] CARPENTER GA, 2003, P INT JOINT C NEUR N
[4] Charitou A., 2004, EUROP ACC REV, V13, P465, DOI DOI 10.1080/0963818042000216811
[5] TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM
HAGAN, MT
MENHAJ, MB
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06): : 989 - 993
[6] JONES M, 2005, P 9 IR AC MAN ANN C
[7] Bankruptcy prediction in banks and firms via statistical and intelligent techniques - A review
Kumar, P. Ravi
Ravi, V.
[J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2007, 180 (01) : 1 - 28
[8] Self organizing neural networks for financial diagnosis
SerranoCinca, C
[J]. DECISION SUPPORT SYSTEMS, 1996, 17 (03) : 227 - 238
[9] Neural-network-based d-step-ahead predictors for nonlinear systems with time delay
Tan, YH
Van Cauwenberghe, A
[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 1999, 12 (01) : 21 - 35

← 1 →