發(fā)布時(shí)間：2018-03-03 12:34

  本文選題：上市公司　切入點(diǎn)：財(cái)務(wù)危機(jī)預(yù)警　出處：《廈門(mén)大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來(lái),我國(guó)A股市場(chǎng)上出現(xiàn)了許多因財(cái)務(wù)問(wèn)題被特別處理的上市公司。由于目前我國(guó)證券市場(chǎng)還處于弱勢(shì)有效階段,集中表現(xiàn)為信息的不對(duì)稱性,所以財(cái)務(wù)危機(jī)不僅使公司自身蒙受巨大損失,還給利益相關(guān)者帶來(lái)了經(jīng)濟(jì)損失和負(fù)面影響,甚至?xí)䦟?duì)市場(chǎng)環(huán)境造成惡劣沖擊。因此,研究如何有效利用公開(kāi)數(shù)據(jù),建立可靠、穩(wěn)定的財(cái)務(wù)危機(jī)預(yù)警模型對(duì)解決上述問(wèn)題能發(fā)揮較為積極的作用。 在介紹了選題背景及研究意義的基礎(chǔ)上,本文明確了研究框架和方法。隨后,系統(tǒng)梳理了國(guó)內(nèi)外學(xué)者在財(cái)務(wù)危機(jī)領(lǐng)域的相關(guān)研究文獻(xiàn),對(duì)財(cái)務(wù)危機(jī)的概念界定、形成原因和預(yù)警理論等方面都進(jìn)行充分的探討,并系統(tǒng)介紹了以往研究中所采用的特征指標(biāo)和建模方法。據(jù)此,界定了實(shí)證分析中財(cái)務(wù)危機(jī)的具體定義,確定了指標(biāo)的初選方向和建模方法。 結(jié)合選定的建模方法,本文詳細(xì)闡述了隨機(jī)森林算法的相關(guān)理論。這一理論結(jié)合了非參數(shù)決策樹(shù)和Bagging算法,對(duì)過(guò)擬合免疫,適用于解決輸入變量多、先驗(yàn)信息不足等復(fù)雜問(wèn)題。本文著重介紹了隨機(jī)森林的特征選擇功能,并指出其變量重要性的計(jì)算結(jié)果是有偏的這一不足,引入了可以計(jì)算變量無(wú)偏條件重要性的條件森林Cforest。 在此基礎(chǔ)上,以A股市場(chǎng)上的234家正常公司和78家ST公司為樣本,本文分別運(yùn)用隨機(jī)森林和Cforest篩選特征指標(biāo),對(duì)比了兩者的選擇結(jié)果,并從財(cái)務(wù)學(xué)角度闡明了Cforest的計(jì)算結(jié)果更具合理性。在確定特征指標(biāo)和最優(yōu)參數(shù)之后,本文建立了基于隨機(jī)森林算法的財(cái)務(wù)危機(jī)預(yù)警模型,在不同的市場(chǎng)行情下運(yùn)用該模型進(jìn)行預(yù)警,并用混淆矩陣評(píng)估其性能。評(píng)估結(jié)果顯示該模型在兩種市場(chǎng)條件下都有較高的準(zhǔn)確率,具有良好的自適應(yīng)性和穩(wěn)定性。為了進(jìn)一步驗(yàn)證隨機(jī)森林模型的高效性,本文還利用了另外一種變量選擇方法Lasso,建立了基于Lasso-logistic回歸的財(cái)務(wù)危機(jī)預(yù)警模型,并對(duì)該模型性能進(jìn)行評(píng)估。評(píng)估結(jié)果顯示,雖然Lasso-logistic預(yù)警模型也能較有效地篩選指標(biāo)和進(jìn)行預(yù)警,但是與隨機(jī)森林預(yù)警模型相比仍然存在一些的局限和不足。 根據(jù)上述的理論研究和實(shí)證分析結(jié)果,本文認(rèn)為基于隨機(jī)森林建立的財(cái)務(wù)危機(jī)預(yù)警模型在市場(chǎng)實(shí)踐中具有較高的實(shí)用價(jià)值,并為上市公司、投資者和債權(quán)人等其他市場(chǎng)參與者提供了相關(guān)參考建議。最后,為能給財(cái)務(wù)危機(jī)預(yù)警實(shí)踐提供更多幫助,本文展望了未來(lái)進(jìn)一步研究的方向。
[Abstract]:In recent years, there have been many listed companies in China's A-share market that have been specially dealt with because of their financial problems. At present, the securities market in China is still in a weak and effective stage, which is concentrated on the asymmetry of information. Therefore, the financial crisis not only makes the company suffer huge losses, but also brings economic losses and negative effects to the stakeholders, and even has a bad impact on the market environment. Stable financial crisis warning model can play a more active role in solving the above problems. On the basis of introducing the background and significance of the research, this paper clarifies the research framework and methods. Then, it systematically combs the relevant research literature of domestic and foreign scholars in the field of financial crisis, and defines the concept of financial crisis. The formation reasons and early warning theory are discussed, and the characteristic indexes and modeling methods used in previous studies are systematically introduced. Based on this, the specific definition of financial crisis in empirical analysis is defined. The primary direction and modeling method are determined. Combined with the selected modeling method, this paper elaborates the related theory of stochastic forest algorithm, which combines the nonparametric decision tree and Bagging algorithm, is immune to over-fitting, and is suitable for solving the problem of multiple input variables. This paper mainly introduces the feature selection function of random forest and points out that the calculation result of its variable importance is biased. A conditional forest Cforestwhich can calculate the importance of variable unbiased condition is introduced. On this basis, with 234 normal companies and 78 St companies in A share market as samples, the selection results of random forest and Cforest were compared. The results of Cforest are more reasonable from the point of view of finance. After determining the characteristic index and optimal parameters, a financial crisis warning model based on stochastic forest algorithm is established in this paper. The model is used for early warning under different market conditions, and its performance is evaluated with confusion matrix. The evaluation results show that the model has high accuracy under both market conditions. It has good self-adaptability and stability. In order to further verify the efficiency of the stochastic forest model, this paper also uses another variable selection method, Lasso, to establish a financial crisis early warning model based on Lasso-logistic regression. The performance of the model is evaluated. The results show that although the Lasso-logistic early warning model can screen indicators and carry out early warning more effectively, there are still some limitations and shortcomings compared with the stochastic forest early warning model. According to the above theoretical research and empirical analysis results, this paper thinks that the financial crisis early warning model based on stochastic forest has higher practical value in the market practice, and it is listed company. Other market participants, such as investors and creditors, provide relevant reference suggestions. Finally, in order to provide more help to the practice of financial crisis warning, this paper looks forward to the direction of further research in the future.
【學(xué)位授予單位】：廈門(mén)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：F275;F276.6;F832.51

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 張鳴,程濤;上市公司財(cái)務(wù)預(yù)警實(shí)證研究的動(dòng)態(tài)視角[J];財(cái)經(jīng)研究;2005年01期

2 林成德;彭國(guó)蘭;;隨機(jī)森林在企業(yè)信用評(píng)估指標(biāo)體系確定中的應(yīng)用[J];廈門(mén)大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年02期

3 武曉巖;李康;;基因表達(dá)數(shù)據(jù)判別分析的隨機(jī)森林方法[J];中國(guó)衛(wèi)生統(tǒng)計(jì);2006年06期

，

本文編號(hào)：1561057