A meta-learning framework for bankruptcy prediction

NCU Institutional Repository > 管理學院 > 資訊管理學系 > 期刊論文 > Item 987654321/106247

請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106247

題名:	A meta-learning framework for bankruptcy prediction
作者:	蔡志豐;Tsai, Chih-Fong;Hsu, Yu-Feng
貢獻者:	管理學院資訊管理學系
關鍵詞:	Bankruptcy;bankruptcy prediction;Comparative analysis;Corporate debt;Decision making;Economic forecasts;Errors;Experiments;Financial institutions;Forecasting techniques;Frame analysis;Interlocking directorates;Learning;Lending;Logistics;Machine learning;meta-learning;Neural networks;Prediction models;Regression analysis;stacked generalization;Studies;Trees
日期:	2013-03-01
上傳時間:	2026-04-23 13:14:51 (UTC+8)
出版者:	John Wiley and Sons Ltd;Chichester: Blackwell Publishing Ltd
摘要:	摘要： The implication of corporate bankruptcy prediction is important to financial institutions when making lending decisions. In related studies, many bankruptcy prediction models have been developed based on some machine‐learning techniques. This paper presents a meta‐learning framework, which is composed of two‐level classifiers for bankruptcy prediction. The first‐level multiple classifiers perform the data reduction task by filtering out unrepresentative training data. Then, the outputs of the first‐level classifiers are utilized to create the second‐level single (meta) classifier. The experiments are based on five related datasets and the results show that the proposed meta‐learning framework provides higher prediction accuracy rates and lower type I/II errors when compared with the stacked generalization classifier and other three widely developed baselines, such as neural networks, decision trees, and logistic regression. Copyright © 2011 John Wiley & Sons, Ltd. 其他題名： J. Forecast 出版者： Chichester: Blackwell Publishing Ltd 出版日期： 2013-03 出處： Journal of forecasting, 2013-03, Vol.32 (2), p.167-179 資源來源： Wiley Online Library - AutoHoldings Journals 版權： Copyright © 2011 John Wiley & Sons, Ltd. 版權： Copyright Wiley Periodicals Inc. Mar 2013 識別號： ISSN: 0277-6693 識別號： EISSN: 1099-131X 識別號： DOI: 10.1002/for.1264 識別號： CODEN: JOFODV
顯示於類別:	[資訊管理學系] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	29	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....