File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Failure prediction of dotcom companies using neural network-genetic programming hybrids

TitleFailure prediction of dotcom companies using neural network-genetic programming hybrids
Authors
KeywordsDotcom companies
f-Statistic
Failure prediction
Feature selection
Genetic programming
Multilayer feed forward neural network
Probabilistic neural network
t-Statistic
Issue Date2010
PublisherElsevier Inc. The Journal's web site is located at http://www.elsevier.com/locate/ins
Citation
Information Sciences, 2010, v. 180 n. 8, p. 1257-1267 How to Cite?
AbstractThis paper presents novel neural network-genetic programming hybrids to predict the failure of dotcom companies. These hybrids comprise multilayer feed forward neural network (MLFF), probabilistic neural network (PNN), rough sets (RS) and genetic programming (GP) in a two-phase architecture. In each hybrid, one technique is used to perform feature selection in the first phase and another one is used as a classifier in the second phase. Further t-statistic and f-statistic are also used separately for feature selection in the first phase. In each of these cases, top 10 features are selected and fed to the classifier. Also, the NN-GP hybrids are compared with MLFF, PNN and GP in their stand-alone mode without feature selection. The dataset analyzed here is collected from Wharton Research Data Services (WRDS). It consists of 240 dotcom companies of which 120 are failed and 120 are healthy. Ten-fold cross-validation is performed throughout the study. Results in terms of average accuracy, average sensitivity, average specificity and area under the receiver operating characteristic curve (AUC) indicate that the GP outperformed all the techniques with or without feature selection. The superiority of GP-GP is demonstrated by t-test at 10% level of significance. Furthermore, the results are much better than those reported in previous studies on the same dataset. © 2009 Elsevier Inc. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/129448
ISSN
2015 Impact Factor: 3.364
2015 SCImago Journal Rankings: 2.513
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorRavisankar, Pen_HK
dc.contributor.authorRavi, Ven_HK
dc.contributor.authorBose, Ien_HK
dc.date.accessioned2010-12-23T08:37:21Z-
dc.date.available2010-12-23T08:37:21Z-
dc.date.issued2010en_HK
dc.identifier.citationInformation Sciences, 2010, v. 180 n. 8, p. 1257-1267en_HK
dc.identifier.issn0020-0255en_HK
dc.identifier.urihttp://hdl.handle.net/10722/129448-
dc.description.abstractThis paper presents novel neural network-genetic programming hybrids to predict the failure of dotcom companies. These hybrids comprise multilayer feed forward neural network (MLFF), probabilistic neural network (PNN), rough sets (RS) and genetic programming (GP) in a two-phase architecture. In each hybrid, one technique is used to perform feature selection in the first phase and another one is used as a classifier in the second phase. Further t-statistic and f-statistic are also used separately for feature selection in the first phase. In each of these cases, top 10 features are selected and fed to the classifier. Also, the NN-GP hybrids are compared with MLFF, PNN and GP in their stand-alone mode without feature selection. The dataset analyzed here is collected from Wharton Research Data Services (WRDS). It consists of 240 dotcom companies of which 120 are failed and 120 are healthy. Ten-fold cross-validation is performed throughout the study. Results in terms of average accuracy, average sensitivity, average specificity and area under the receiver operating characteristic curve (AUC) indicate that the GP outperformed all the techniques with or without feature selection. The superiority of GP-GP is demonstrated by t-test at 10% level of significance. Furthermore, the results are much better than those reported in previous studies on the same dataset. © 2009 Elsevier Inc. All rights reserved.en_HK
dc.languageengen_US
dc.publisherElsevier Inc. The Journal's web site is located at http://www.elsevier.com/locate/insen_HK
dc.relation.ispartofInformation Sciencesen_HK
dc.subjectDotcom companiesen_HK
dc.subjectf-Statisticen_HK
dc.subjectFailure predictionen_HK
dc.subjectFeature selectionen_HK
dc.subjectGenetic programmingen_HK
dc.subjectMultilayer feed forward neural networken_HK
dc.subjectProbabilistic neural networken_HK
dc.subjectt-Statisticen_HK
dc.titleFailure prediction of dotcom companies using neural network-genetic programming hybridsen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0020-0255&volume=180&issue=8&spage=1257&epage=1267&date=2010&atitle=Failure+prediction+of+dotcom+companies+using+neural+network-genetic+programming+hybrids-
dc.identifier.emailBose, I: bose@business.hku.hken_HK
dc.identifier.authorityBose, I=rp01041en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.ins.2009.12.022en_HK
dc.identifier.scopuseid_2-s2.0-75149191307en_HK
dc.identifier.hkuros177557en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-75149191307&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume180en_HK
dc.identifier.issue8en_HK
dc.identifier.spage1257en_HK
dc.identifier.epage1267en_HK
dc.identifier.isiWOS:000275139300005-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridRavisankar, P=35307820600en_HK
dc.identifier.scopusauthoridRavi, V=15770237000en_HK
dc.identifier.scopusauthoridBose, I=7003751502en_HK
dc.identifier.citeulike6500844-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats