篇名 | 運用類神經網路建構臺灣地區農會信用部金融預警系統 |
---|---|
卷期 | 68、68 |
並列篇名 | Application of the Neural Networks to Establish a Financial Early Warning System for Credit Departments of Farmers' Associations in Taiwan |
作者 | 蔡碩倉 |
頁次 | 117-156 |
關鍵字 | 農會信用部 、 金融預警系統 、 倒傳遞類神經網路 、 Credit department of farms' associations 、 Financial early warning system 、 Back-propagation neural network 、 TSSCI |
出刊日期 | 200012 |
本文旨在結合企業經營危機理論與投資組合理論,並搭配倒傳遞類神經網路預警模型,量身裁製符合臺灣地區農會信用部經營特性之金融預警系統。研究結果顯示,農會信用部經營良窳係屬不同投資組合下之槓桿操作結果,而複的投資組合間存在程度上不同之抵換關係,須藉由金融預警系統綜合判定其營運等級。至於擠兌應以單純引發事件視之,並無法衍生為經營不善關系,否則將嚴重產生統計上型I與型II誤差。另農會信用部於經營失敗過程中具有明顯的危機警訊可供金融預警系統事前偵測,蓋農會信用經營失敗過程具有連續軌跡可供搜尋,而此連續過程亦代表不同營運評等等級之差異展現。
This study combines the business crisis and portfolio theories, together with theback-propagation neural network, to establish a financial early warning system catering to theoperation needs of credit departments of farmers' associations in Taiwan.The empirical results show that the management performance of a credit department is highlyrelated to its financial leverage operations among different portfolios, among which there existtrade-off relations, and that the ratings of the portfolio operations may be derived by the financialearly warning system. Cases of bank runs should be viewed as exceptional due to their weaklinkages to operational crises. Otherwise, Type-I and Type-II errors in statistics might occur.Furthermore, this early earning system is able to detect in advance the signs of crises caused by theoperation failures of a credit department because there are continuous traces of the process ofoperation failures and these continuous traces signify the differences of various operation ratings.