由於財務報表資訊易遭管理當局操縱，因此財務預警模型若僅考慮財務比率變數，即有其限制。本研究因此結合財務比率變數與公司治理變數，以期建構更良好的財務預警模型。此外，本研究使用倒傳遞網路為工具，以避免前述限制，並預期結果顯示綜合採用財務比率及公司治理二類變數，在預測期間短時，所建立的財務預警模型，其錯誤率的確較低。本研究同時發現，樣本公司中的危機公司大多屬於「急速失敗公司」。 / Early warning models used to predict financial distresses of corporations confront with limitation, when the model specification consider only financial ratios based on financial statements, because of the possibility of manipulated financial statements. This study intends to construct a early warning model with not only financial ratio variables, but also corporate governance variables. The corporate governance variables may affect the corporation with financial distresses dramatically. This study constructs a new early warning model, considering the two kinds of variables, both financial ratio and corporate governance, and improves the predictability of sample firms of the one-quarter period. The study shows that Back Propagation Neural Network model can learn from the data of failed corporations and a matched group of survivor firms and hence predict the financial distresses. The study also finds the sample failed corporations are more likely to be “acute failure” ones. Keyword: BPN, Corporate Governance, Financial Distresses.

由於時間序列在不同範疇的廣泛應用，許多實證結果已明白指出時間序列 資料普遍地存在非線性(nonlinearity)，使得非線型方法在最近幾年受到 極大的重視。然而，對於某些特定的非線型模式，縱然現在已有學者提出 模式選取之檢定方法，但是它們的模式階數確認問題至今卻仍無法有效率 地解決，更遑論得到最佳的模式配適與預測結果了。所以，我們試圖利用 一已於其他科學領域成功應用之新技術──神經網路，來解決非線型時間 序列之預測問題，而我們之所以利用神經網路的原因是其多層前輸網路是 泛函數的近似器(functional approximator)，對任意函數均有極佳之逼 近能力，使我們免除對時間序列資料之屬性(線性或非線性)作事先檢定或 假設的必要。在本篇論文中，我們首先建構15組雙線型時間序列資料，然 後對於這些數據分別以神經網路與自我迴歸整合移動平均(ARIMA) 模式配 適。藉著比較兩者間的配適與預測結果，我們發現神經網路對於預測非線 型時間序列是較具有穩健性。最後，我們以台幣對美元之即期匯率作為我 們的實證資料，結果亦證實了神經網路對於預測一般經濟時間序列亦較具 穩健性。 / With rapid development at the study of time series, the nonlinear approaches have attracted great attention in recent years. However, there are no efficient processes for the problem of identification to many specifically nonlinear models . Even if many testing methods have been proposed, we still can not find the best fitted model and obtain the best forecast performance. Hence, we try to solve the forecast problems by a new technique -- neurocomputing, which has been successfully applied in many scientific fields. The reason why we apply the neural networks is that the multilayer feedforward networks are functional approximators for the unknown function. In this paper, we will first construct several sets of bilinear time series and then fit these series by neural networks and ARIMA models. In this simulation study, we have found that the neural networks perform the robust forecast for some nonlinear time series. Finally, forecasting performance with favorable models will also be compared through the empirical realization of Taiwan.

本篇論文旨在分析神經網路學習績效，並提出一套學習演算法，結合倒傳遞網路(BP)與理解神經網路(RN)，命名為RNBP，這套學習演算法將與傳統的BP做比較，以兩個不同的財務金融領域的應用，一個是選擇權上Black-Scholes訂價模式的模擬，一個是金融交換上利率的預測。主要績效的評估準則是以學習的效率與模擬、預測的準確度為依據。 此外，本論文的另一個重點是提出一套對於神經網路系統進一步分析的方法與工具，敏感度分析(Sensitivity Analysis)與滯留區(Dead Region)分析，藉以瞭解神經網路系統是否具有效地良好學習或被一般化的能力，從神經網路的角度來說，這也是BP與RNBP的另一個績效比較標準。本研究的結果顯示RNBP在預測準確度上較BP為優良，但是在學習效率與預測能力的穩定性上並沒有呈現一致性的結論；此外，敏感度分析與滯留區分析的結果也幫助神經網路在應用領域上有更深入的瞭解。 在過去，神經網路的應用者往往忽略了進一步瞭解神經網路的重要性與可行性，本論文的貢獻在於藉由分析神經網路所學習的知識，幫助應用者進一步瞭解神經網路表達的訊息在應用領域上所隱含的實質意義。 / The study attempts to analyze the learning performance of neural networks in applications, and propose a new learning procedure for the layered feedforward neural network systems, named KNBP, which binds RN and BP learning algorithms. Two artificial neural networks, BP and KNBP, here are both applied to two financial fields, the simulation of Black-Scholes pricing model for the call options and the midrates forecasting in financial swaps. The explicit performance comparison between the two artificial neural network systems is mainly based on two criteria, which are learning efficiency and forecasting effectiveness. Then we propound a mathematical methodology of sensitivity analysis and the dead regions to deeply explore inside the network structures to see whether the models of ANNS are actually well trained or valid, and thus setup an alternative comparable criterion. The results from this study show that RNBP performs better than BP in forecasting effectiveness, but RNBP obtains neither a consistent learning efficiency in cases nor a stable forecasting ability. Furthermore, the sensitivity analysis and the dead region analysis provide a deeper view of the ANNs in the applied fields. In the past, most studies applying neural networks ignored the importance that it is feasible and advantageous to obtain more useful information via analyzing neural networks. The purpose of the research is to help further understanding to the information discovery resulted from neural networks in practical applications.

學界間廣泛地認為一般金融資產報酬具有的特性是:線型不可預測性,條件 異質變異數,非條件尖峰態 ... 等特性o 固然金融資產報酬具有線型不可 預測之特性,可是並不能否決其間可能有非線型依存關係的存在o目前大部 份經濟計量分析方法中的模式建構問題均是在假設模式的結構訊息已知的 條件下求解,然若真實體系的結構訊息未知或不明朗時,貿然地假設為某種 特定的模式結構,則可能又難於避免模式設定錯誤的困擾,因而對於真實體 系行為的描述亦將可能是誤導且不合理的,這意味著:除非該特定的模式結 構正是真實體系的表徵, 否則無論該特定模式的結構特性多完美,均難以 建構一令人信服的數理化模式來表徵真實體系之行為o 不幸地,此一問題 在高度非線型的動態隨機體系中尤其嚴重, 甚至是否存在一 ``真實'' 模式來據以表徵體系之行為,亦是相當值得懷疑, 故考慮一種無需特定結 構訊息假設的無母數方法或函數逼近法實屬必要o 類神經網路中的倒傳遞 網路模式即是符合此種特性的方法之一o然而學界間仍無法確定的是金融 資產報酬序列資料所產生的 ARCH 效果本身是否為真實序列資料產生機制 特性之顯現, 還是應歸咎於被忽略掉條件均數方面之非線性所衍生模式設 定錯誤情況下的代用模式, 並不得而知;另一方面, ARCH 模式的顯著成就 及其價值亦不能予以輕易地漠視, 因此, 試圖將 ARCH 模式所能提供的攸 關訊息納入倒傳遞網路模式的考量之中而形成倒傳遞網路-自迴歸條件異 質變異數 (BPN-ARCH) 模式以增進樣本外預測能力的精度便是本論文最 主要的嘗試重點與目的o