本研究運用整合多元適應性雲形迴歸(multivariate adaptive regression splines, MARS)與類神經網路的兩階段模式,建構企業危機診斷分類模式。且在探討企業危機的衡量指標上,除參考一般傳統財務指標外,另加入智慧資本指標與公司治理指標,希望能藉由更完整多元的企業資訊,建立新的企業危機診斷模式。依實證結果發現,經由MARS針對所考量之衡量企業危機指標進行分析,得知企業失敗除了受到傳統財務構面指標的影響外,亦受到智慧資本與公司治理構面指標的影響。此外,有關整合MARS與類神經網路方法所建構之企業危機診斷模式,亦能有效的降低企業危機診斷的誤判情況、增加時效性,是以無論在學術研究或實務工作上,實有其相當之助益。
The objective of the proposed study is to investigate the performance of enterprise distress diagnosis using artificial neural networks with multivariate adaptive regression splines (MARS) analysis technique. In addition to the traditional financial ratios, the intellectual capital (IC) and corporate governance indicators are also included in the model to measure the assets of companies. The statistical analysis applied in data analysis included Wilcoxon signed-rank test, and Friedman rank test analysis of variance by ranks. The results indicate that the proposed combined approach provides higher classification accuracy and converges much faster than the conventional neural network approach. Moreover, the results also indicate that traditional financial indicators、IC and corporate governance indicators all contribute to improving the classification accuracy of the build diagnostic model.
為了持續優化網站功能與使用者體驗,本網站將Cookies分析技術用於網站營運、分析和個人化服務之目的。
若您繼續瀏覽本網站,即表示您同意本網站使用Cookies。