發(fā)布時(shí)間：2018-06-19 02:39

  本文選題：退市預(yù)警 + 支持向量機(jī)　； 參考：《華南理工大學(xué)》2013年碩士論文

【摘要】：退市制度是資本市場(chǎng)整體框架構(gòu)成的重要組成部分，一個(gè)健康合理的資本市場(chǎng)既要保證經(jīng)營(yíng)業(yè)績(jī)好的企業(yè)能進(jìn)場(chǎng)，又要保證經(jīng)營(yíng)效益差的企業(yè)被清理出場(chǎng)。我國(guó)已于2012年相繼頒布了創(chuàng)業(yè)板退市新規(guī)和主板與中小板退市新規(guī)，這標(biāo)志著我國(guó)證券市場(chǎng)多年來(lái)上市公司有進(jìn)無(wú)退歷史的終結(jié)。 退市風(fēng)險(xiǎn)存在于我國(guó)滬深兩市中的部分上市公司之中，尤其是ST標(biāo)志上市公司。對(duì)于上市公司風(fēng)險(xiǎn)識(shí)別和處置是保證公司有效運(yùn)行的核心內(nèi)容，建立有價(jià)值的上市公司退市風(fēng)險(xiǎn)預(yù)警模型，盡早識(shí)別上市公司是否有退市風(fēng)險(xiǎn)，有利于做到風(fēng)險(xiǎn)的事前控制，這是保證投資者合法權(quán)益，，降低市場(chǎng)風(fēng)險(xiǎn)的有效途徑。 本文使用SVM_AdaBoost強(qiáng)分類(lèi)器模型構(gòu)建上市公司退市預(yù)警模型。支持向量機(jī)（SVM）是數(shù)據(jù)挖掘中的新方法，AdaBoost算法作為一種通用的學(xué)習(xí)算法，可以提高任一給定算法的性能。使用AdaBoost算法連接若干個(gè)不同核函數(shù)的SVM，可以得到分類(lèi)精度更高的強(qiáng)分類(lèi)器SVM_AdaBoost模型。本文選取200家上市公司作為樣本，先粗選17個(gè)指標(biāo)，后使用獨(dú)立樣本T檢驗(yàn)精選9個(gè)指標(biāo)作為預(yù)警指標(biāo)。然后對(duì)9個(gè)指標(biāo)進(jìn)行歸一化處理，消除量綱差異的影響，最終使用AdaBoost算法構(gòu)建基于徑向基核函數(shù)和多項(xiàng)式核函數(shù)的10個(gè)不同的SVM的SVM_AdaBoost強(qiáng)分類(lèi)器，進(jìn)行退市預(yù)警。研究發(fā)現(xiàn)：相對(duì)單一SVM，SVM_AdaBoost對(duì)70家測(cè)試樣本公司的分類(lèi)性能由92.8571%提高到95.7143%，這顯示了SVM_AdaBoost強(qiáng)分類(lèi)器模型有較在退市預(yù)警研究中有較好的應(yīng)用價(jià)值。
[Abstract]:The delisting system is an important part of the overall framework of the capital market. A healthy and reasonable capital market should not only guarantee the entry of enterprises with good operating performance, but also ensure that enterprises with poor operating efficiency are cleared out. In 2012, China has promulgated the new rules for delisting of gem and the new rules for delisting of main board and small board, which marks the end of the history of listed companies in the stock market of our country for many years. Delisting risk exists in some listed companies in Shanghai and Shenzhen stock markets, especially St mark listed companies. Risk identification and disposal of listed companies is the core content to ensure the effective operation of the company. Establishing a valuable early warning model of delisting risks of listed companies and identifying whether there are delisting risks of listed companies as soon as possible is beneficial to the prior control of risks. This is an effective way to ensure the legitimate rights and interests of investors and reduce market risks. In this paper, SVMAdaBoost strong classifier model is used to construct the delisting warning model of listed companies. Support Vector Machine (SVM) is a new method in data mining. As a general learning algorithm, AdaBoost algorithm can improve the performance of any given algorithm. Using AdaBoost algorithm to connect several SVMs with different kernels, a stronger SVMStackAdaBoost model with higher classification accuracy can be obtained. In this paper, 200 listed companies are selected as samples, 17 indexes are selected first, and then 9 indexes selected by independent sample T test are used as early warning indexes. Then the nine indexes are normalized to eliminate the influence of dimensional difference. Finally, the SVMAdaBoost strong classifier of 10 different SVM based on radial basis function and polynomial kernel function is constructed using AdaBoost algorithm to carry out delisting warning. It is found that the classification performance of SVM _ S _ AdaBoost is improved from 92.8571% to 95.7143%, which shows that SVM _ AdaBoost strong classifier model has better application value in delisting and early warning research.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：F832.51;F224

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馮蕓;劉艷琴;;上市公司退市制度實(shí)施效果的實(shí)證分析[J];財(cái)經(jīng)研究;2009年01期

2 黃繼鴻,雷戰(zhàn)波,凌超;經(jīng)濟(jì)預(yù)警方法研究綜述[J];系統(tǒng)工程;2003年02期

3 梁琪;企業(yè)經(jīng)營(yíng)管理預(yù)警:主成分分析在logistic回歸方法中的應(yīng)用[J];管理工程學(xué)報(bào);2005年01期

4 孫星,邱菀華;企業(yè)財(cái)務(wù)危機(jī)預(yù)警雙基點(diǎn)距離比值法[J];管理工程學(xué)報(bào);2005年03期

5 周敏,王新宇;基于模糊優(yōu)選和神經(jīng)網(wǎng)絡(luò)的企業(yè)財(cái)務(wù)危機(jī)預(yù)警[J];管理科學(xué)學(xué)報(bào);2002年03期

6 武勃,黃暢,艾海舟,勞世z

本文編號(hào)：2038001