頁籤選單縮合
題名 | 以支援向量機與羅吉斯迴歸進行企業危機診斷之比較=A Compared Study to Diagnose a Business Crisis by Using Support Vector Machine and Logit Regression |
---|---|
作者 | 蕭慧德; 周萍芬; 邱清顯; | 書刊名 | 遠東學報 |
卷期 | 25:2 2008.06[民97.06] |
頁次 | 頁333-342 |
分類號 | 494.7 |
關鍵詞 | 支援向量機; 羅吉斯迴歸; 企業危機; 智慧資本; SVM; Logit; Business crises; Intellectual capital; |
語文 | 中文(Chinese) |
中文摘要 | 本研究以SVM 對資料的學習與分類的能力,建構企業危機診斷模型,並經鑑別分析進行特徵選擇後,進行SVM 與Logit 迴歸的比較,模型實際運作後,對所測試的企業資料能提供高達7.11% 準確率的預警。經過篩選出來對企業危機最具影響力的特徵值,其中包含了財務與智慧資本的特徵值,這些特徵值平凡到隨時都可以在企業的公開資料中獲得,它也提供了企業經營者可以隨時對企業做簡單自我檢測,以瞭解企業是否正面臨危機。 |
英文摘要 | This research is aimed at establishing the diagnosis models for business crises through SVM to perform learning and classification on data. After finishing the training processes, the proposed SVM can reach a prediction accuracy of 87.11% for all the tested business data compared with Logit regression. Particularly, these influential features are included in the proposed model with intellectual capital and financial features after the selecting process; these features are ordinary and widely available from public business reports. The proposed SVM is available for business managers to conduct self-diagnosis in order to realize whether business units are really facing a crisis. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。