dc.contributor.author | Charalambous, Chris | en |
dc.contributor.author | Charitou, Andreas | en |
dc.contributor.author | Kaourou, Froso | en |
dc.coverage.spatial | Piscataway, NJ, United States | en |
dc.creator | Charalambous, Chris | en |
dc.creator | Charitou, Andreas | en |
dc.creator | Kaourou, Froso | en |
dc.date.accessioned | 2019-04-24T06:29:23Z | |
dc.date.available | 2019-04-24T06:29:23Z | |
dc.date.issued | 2000 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/46689 | en |
dc.description.abstract | This study uses the feature selection algorithm proposed by Setiono and Liu to select the most relevant features for the bankruptcy prediction problem. The method uses a feedforward neural network with one hidden layer to decide which features to be removed. Our data consists of 139 matched pair of bankrupt and nonbankrupt U.S. firms for the period 1983-1994. The results of this study indicate that the final neural network obtained with reduced number of inputs gives significantly better prediction results than the one that uses all initial features. | en |
dc.language.iso | eng | en |
dc.publisher | IEEE | en |
dc.source | Proceedings of the International Joint Conference on Neural Networks | en |
dc.subject | Algorithms | en |
dc.subject | Bankruptcy prediction | en |
dc.subject | Feature extraction | en |
dc.subject | Feature selection algorithms | en |
dc.subject | Feedforward neural networks | en |
dc.title | Application of feature extractive algorithm to bankruptcy prediction | en |
dc.type | info:eu-repo/semantics/conferenceObject | |
dc.description.volume | 5 | |
dc.description.startingpage | 303 | |
dc.description.endingpage | 308 | |
dc.author.faculty | Σχολή Οικονομικών Επιστημών και Διοίκησης / Faculty of Economics and Management | |
dc.author.department | Τμήμα Λογιστικής και Χρηματοοικονομικής / Department of Accounting and Finance | |
dc.type.uhtype | Conference Object | en |
dc.contributor.orcid | Charitou, Andreas [0000-0003-1080-9121] | |
dc.description.totalnumpages | 303-308 | |
dc.gnosis.orcid | 0000-0003-1080-9121 | |