FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207190011> ?p ?o ?g. }

• W3207190011 endingPage "101455" @default.
• W3207190011 startingPage "101455" @default.
• W3207190011 abstract "• An optimum deep learning architecture is proposed using a panel data structure to predict corporate failure. • Based on a large sample of US distressed and bankrupt firms, the deep learning model achieves an overall out-of-sample accuracy rate of 91.2%. • Deep learning performs significantly better than discrete hazard models in predicting corporate failure (the model is 93.71% accurate out-of-sample compared to 86.95% for discrete hazard model). • Deep learning can be applied to many other classification problems in finance involving panel data structures, such as mergers and takeovers, ratings changes and auditor going concern evaluations. In recent years, deep learning has emerged as a dominant machine learning method used in a variety of applications, including robotics (such as self-driving cars), speech recognition, text analysis and natural language processing, fraud detection, earthquake prediction, medical image analysis just to mention a few applications. In this paper, we propose an optimum deep learning model using a panel data structure to predict corporate failure. We compare deep learning with the more traditional discrete hazard model which has been widely applied in the finance literature in panel data applications (such as bankruptcy prediction). Based on a sample of 641,667 firm-month observations of North American listed companies between 2001 and 2018 and including many financial and market-based feature variables, our deep learning model can predict corporate failure with 93.71% accuracy. This is significantly more accurate than the discrete hazard model which predicted corporate failure with only 86.95% accuracy. Not only has our deep learning model proven highly effective in corporate failure prediction but it can be potentially applied to many other classification problems in finance involving panel data structures." @default.
• W3207190011 created "2021-10-25" @default.
• W3207190011 creator A5015243228 @default.
• W3207190011 creator A5015817857 @default.
• W3207190011 creator A5018034867 @default.
• W3207190011 date "2021-11-01" @default.
• W3207190011 modified "2023-09-27" @default.
• W3207190011 title "Corporate failure prediction: An evaluation of deep learning vs discrete hazard models" @default.
• W3207190011 cites W1964159032 @default.
• W3207190011 cites W19790595 @default.
• W3207190011 cites W1988221687 @default.
• W3207190011 cites W1992958333 @default.
• W3207190011 cites W1993229844 @default.
• W3207190011 cites W2004932854 @default.
• W3207190011 cites W2005596732 @default.
• W3207190011 cites W2006680549 @default.
• W3207190011 cites W2008301397 @default.
• W3207190011 cites W2020245109 @default.
• W3207190011 cites W2020848494 @default.
• W3207190011 cites W2032784723 @default.
• W3207190011 cites W2041255922 @default.
• W3207190011 cites W2045512849 @default.
• W3207190011 cites W2048801439 @default.
• W3207190011 cites W2081320339 @default.
• W3207190011 cites W2084232675 @default.
• W3207190011 cites W2101726556 @default.
• W3207190011 cites W2124532504 @default.
• W3207190011 cites W2126017757 @default.
• W3207190011 cites W2135606128 @default.
• W3207190011 cites W2150164326 @default.
• W3207190011 cites W2183020880 @default.
• W3207190011 cites W2510541067 @default.
• W3207190011 cites W2607162077 @default.
• W3207190011 cites W2618249137 @default.
• W3207190011 cites W2626475703 @default.
• W3207190011 cites W2800569739 @default.
• W3207190011 cites W2890297193 @default.
• W3207190011 cites W2923901687 @default.
• W3207190011 cites W2925317631 @default.
• W3207190011 cites W2946440468 @default.
• W3207190011 cites W2952327533 @default.
• W3207190011 cites W2962957157 @default.
• W3207190011 cites W2963099737 @default.
• W3207190011 cites W2963268748 @default.
• W3207190011 cites W2991096480 @default.
• W3207190011 cites W2995432075 @default.
• W3207190011 cites W3121356370 @default.
• W3207190011 cites W3121727765 @default.
• W3207190011 cites W3122632517 @default.
• W3207190011 cites W3123829312 @default.
• W3207190011 cites W3125168868 @default.
• W3207190011 cites W3138448766 @default.
• W3207190011 cites W4206444459 @default.
• W3207190011 doi "https://doi.org/10.1016/j.intfin.2021.101455" @default.
• W3207190011 hasPublicationYear "2021" @default.
• W3207190011 type Work @default.
• W3207190011 sameAs 3207190011 @default.
• W3207190011 citedByCount "6" @default.
• W3207190011 countsByYear W32071900112022 @default.
• W3207190011 countsByYear W32071900112023 @default.
• W3207190011 crossrefType "journal-article" @default.
• W3207190011 hasAuthorship W3207190011A5015243228 @default.
• W3207190011 hasAuthorship W3207190011A5015817857 @default.
• W3207190011 hasAuthorship W3207190011A5018034867 @default.
• W3207190011 hasConcept C144133560 @default.
• W3207190011 hasConcept C149782125 @default.
• W3207190011 hasConcept C154945302 @default.
• W3207190011 hasConcept C162118730 @default.
• W3207190011 hasConcept C178790620 @default.
• W3207190011 hasConcept C185592680 @default.
• W3207190011 hasConcept C2991902670 @default.
• W3207190011 hasConcept C33923547 @default.
• W3207190011 hasConcept C41008148 @default.
• W3207190011 hasConcept C49261128 @default.
• W3207190011 hasConceptScore W3207190011C144133560 @default.
• W3207190011 hasConceptScore W3207190011C149782125 @default.
• W3207190011 hasConceptScore W3207190011C154945302 @default.
• W3207190011 hasConceptScore W3207190011C162118730 @default.
• W3207190011 hasConceptScore W3207190011C178790620 @default.
• W3207190011 hasConceptScore W3207190011C185592680 @default.
• W3207190011 hasConceptScore W3207190011C2991902670 @default.
• W3207190011 hasConceptScore W3207190011C33923547 @default.
• W3207190011 hasConceptScore W3207190011C41008148 @default.
• W3207190011 hasConceptScore W3207190011C49261128 @default.
• W3207190011 hasLocation W32071900111 @default.
• W3207190011 hasOpenAccess W3207190011 @default.
• W3207190011 hasPrimaryLocation W32071900111 @default.
• W3207190011 hasRelatedWork W1533141389 @default.
• W3207190011 hasRelatedWork W2080579974 @default.
• W3207190011 hasRelatedWork W2124753515 @default.
• W3207190011 hasRelatedWork W2131006951 @default.
• W3207190011 hasRelatedWork W2410036091 @default.
• W3207190011 hasRelatedWork W3107474891 @default.
• W3207190011 hasRelatedWork W3121198219 @default.
• W3207190011 hasRelatedWork W3122003771 @default.
• W3207190011 hasRelatedWork W3124245819 @default.
• W3207190011 hasRelatedWork W2188825458 @default.
• W3207190011 hasVolume "75" @default.

• next