本文選題：VaR + 深度學(xué)習(xí)�。� 參考：《蘭州財(cái)經(jīng)大學(xué)》2017年碩士論文

【摘要】：在美國(guó)次貸危機(jī)的影響下,全球經(jīng)濟(jì)遭遇重創(chuàng)。盡管次貸危機(jī)現(xiàn)在已經(jīng)漸漸遠(yuǎn)離,但它所產(chǎn)生的傷害仍然繼續(xù),使得人們不得不反思其背后的原因,金融風(fēng)險(xiǎn)管理就是在這個(gè)時(shí)候逐漸被重新強(qiáng)調(diào)起來(lái)的。金融市場(chǎng)風(fēng)險(xiǎn)是由金融資產(chǎn)未來(lái)波動(dòng)的不確定性引起的。由于金融資產(chǎn)的波動(dòng)會(huì)帶動(dòng)其價(jià)值的波動(dòng),這些波動(dòng)一方面造就了金融市場(chǎng)的活躍性和流動(dòng)性,使得各種經(jīng)濟(jì)資產(chǎn)表現(xiàn)為價(jià)值運(yùn)動(dòng),但另一方面也會(huì)導(dǎo)致經(jīng)濟(jì)過(guò)渡虛擬,風(fēng)險(xiǎn)和不確定性將被無(wú)限放大,給投資人、企業(yè)、社會(huì)、國(guó)家?guī)?lái)巨大損失,甚至引發(fā)金融危機(jī)。金融風(fēng)險(xiǎn)管理就是要通過(guò)各種技術(shù)手段找出各個(gè)投資組合的最大可能損失,并在此基礎(chǔ)上進(jìn)行分析與決策,從而維護(hù)金融市場(chǎng)健康穩(wěn)定的發(fā)展。金融風(fēng)險(xiǎn)度量(Financial risk metrics)是金融風(fēng)險(xiǎn)管理中的核心與根本,是金融風(fēng)險(xiǎn)管理的最優(yōu)先問(wèn)題,它對(duì)金融風(fēng)險(xiǎn)管理起著杠桿的作用。傳統(tǒng)的金融風(fēng)險(xiǎn)度量方法是以國(guó)外學(xué)者發(fā)明的波動(dòng)率方法為代表,通過(guò)測(cè)算金融資產(chǎn)收益率的方差或標(biāo)準(zhǔn)差來(lái)度量風(fēng)險(xiǎn)大小。由于它只描述了金融資產(chǎn)收益的偏離程度,不能對(duì)偏離的方向和損失水平進(jìn)行說(shuō)明,導(dǎo)致其應(yīng)用有限,因而不再很好的適應(yīng)快速變化的金融發(fā)展。VaR作為一種新的金融風(fēng)險(xiǎn)度量工具問(wèn)世,打破了以波動(dòng)率方法為代表的傳統(tǒng)度量方法的統(tǒng)治地位。它通過(guò)對(duì)金融風(fēng)險(xiǎn)進(jìn)行定量的計(jì)算,從而有效的進(jìn)行風(fēng)險(xiǎn)分析,更直觀的揭露風(fēng)險(xiǎn),因而在對(duì)金融市場(chǎng)風(fēng)險(xiǎn)度量上得到了廣泛的應(yīng)用,同時(shí)對(duì)金融風(fēng)險(xiǎn)的量化管理也起到了顯著的效果。這使得VaR迅速成為標(biāo)桿,并普遍的被應(yīng)用于金融市場(chǎng)風(fēng)險(xiǎn)的度量中。盡管VaR的研究歷史悠久。但現(xiàn)有的關(guān)于VaR計(jì)算方法改進(jìn)的研究并不多,大部分都集中于研究VaR在各個(gè)領(lǐng)域中的應(yīng)用。尤其是我國(guó)對(duì)VaR的研究起步相對(duì)較晚,其中較多的研究是基于國(guó)外已經(jīng)成熟的研究成果,從它們的概念、原理、方法以及運(yùn)用VaR方法進(jìn)行實(shí)證研究等方面來(lái)說(shuō)明,鮮有學(xué)者對(duì)VaR計(jì)算方法提出架構(gòu),因而忽視了基于VaR的風(fēng)險(xiǎn)測(cè)量中存在的一些缺陷。VaR方法是通過(guò)對(duì)金融資產(chǎn)過(guò)去的收益特征進(jìn)行統(tǒng)計(jì)分析來(lái)估算未來(lái)可能發(fā)生的最大損失。因此,在計(jì)算VaR的過(guò)程中其精度的高低依賴(lài)于對(duì)所研究的金融資產(chǎn)收益率的分布的假設(shè)和對(duì)其方差的估計(jì)。這意味著,基于VaR的風(fēng)險(xiǎn)測(cè)量方法存在著對(duì)樣本數(shù)據(jù)特征的認(rèn)識(shí)不足問(wèn)題,將導(dǎo)致風(fēng)險(xiǎn)測(cè)量的不準(zhǔn)確,甚至產(chǎn)生較大的偏差。同時(shí)科技的進(jìn)步,金融市場(chǎng)的不斷變革,使得人工智能在金融分析管理中越來(lái)越重要,并引起了學(xué)者的高度關(guān)注。近幾年,利用深度學(xué)習(xí)處理大數(shù)據(jù)更是掀起了一股技術(shù)方法創(chuàng)新浪潮。給量化金融市場(chǎng)風(fēng)險(xiǎn)上增添了強(qiáng)有力的工具,突破了金融風(fēng)險(xiǎn)度量的盲區(qū)。股票市場(chǎng)是預(yù)測(cè)未來(lái)實(shí)體經(jīng)濟(jì)發(fā)展和調(diào)動(dòng)資金流向的重要場(chǎng)所,也是金融市場(chǎng)重要的極重要的一部分。因?yàn)楣善笔袌?chǎng)不僅僅是募集資金的場(chǎng)所,它也是是公眾投資理財(cái)?shù)闹匾馈９善笔袌?chǎng)中的股票作為融資理財(cái)?shù)膽{證,與人們的經(jīng)濟(jì)活動(dòng)息息相關(guān)。而且,股票投資的本身也是進(jìn)行風(fēng)險(xiǎn)投資。因而,股票市場(chǎng)的波動(dòng)性可以反映出金融風(fēng)險(xiǎn)的波動(dòng)性,且可以用它來(lái)研究金融風(fēng)險(xiǎn)的度量方法。綜上,研究股票市場(chǎng)的波動(dòng)性有著代表性意義。因此,本文以我國(guó)的股票市場(chǎng)為例,在已有文獻(xiàn)的基礎(chǔ)上,針對(duì)目前VaR方法存在的缺陷,提出了基于深度學(xué)習(xí)的VaR測(cè)算。首先對(duì)傳統(tǒng)意義上的損失進(jìn)行改進(jìn),使用預(yù)期損失,從而更加符合現(xiàn)實(shí)中人們對(duì)損失的多樣化定義。其次,分別對(duì)股票收益率數(shù)據(jù)建立ARCH族模型以及對(duì)預(yù)期損失建立深度人工神經(jīng)網(wǎng)絡(luò)模型,進(jìn)而對(duì)VaR進(jìn)行更加精確的預(yù)測(cè)。經(jīng)實(shí)證發(fā)現(xiàn),在深度學(xué)習(xí)下的VaR計(jì)算比ARCH族模型下的VaR計(jì)算更加精確。說(shuō)明基于深度學(xué)習(xí)的VaR計(jì)算具有更好的實(shí)用性。
[Abstract]:Under the impact of the American subprime crisis, the global economy has been hit hard. Although the subprime crisis is now getting far away, the damage it produces continues to cause people to reflect on the reasons behind it. Financial risk management is gradually reemphasized at this time. The risk of financial markets is the future of financial assets. The volatility of volatility causes the volatility of the value of financial assets. These fluctuations, on the one hand, create the activity and liquidity of the financial market, and make all kinds of economic assets as a value movement, but on the other hand, the economic transition will also lead to the virtual economic transition, and the risks and uncertainties will be magnified indefinitely. The enterprises, the society and the state bring huge losses and even lead to the financial crisis. Financial risk management means to find out the greatest possible losses of each portfolio by various technical means, and to analyze and make decisions on this basis so as to maintain the healthy and stable development of the financial market. The financial risk measurement (Financial risk metrics) is the finance. The core and fundamental of risk management is the most important problem in the management of financial risk. It plays a lever role in the management of financial risk. The traditional method of financial risk measurement is represented by the method of volatility invented by foreign scholars, measuring the risk by measuring the variance or standard deviation of the yield of financial assets. Because it is only described. The deviation degree of the financial assets income can not be explained in the direction of deviation and the level of loss, which leads to the limited application of the financial development, which is no longer good to adapt to the rapid change of financial development.VaR as a new financial risk measurement tool, breaking the dominant position of the traditional measurement method represented by the method of volatility. The quantitative calculation of financial risk, so as to effectively carry on the risk analysis, more intuitively expose the risk, has been widely used in the financial market risk measurement, and also has played a significant effect on the quantitative management of financial risk. This makes VaR quickly become a benchmark and is widely used in the financial market. In the measurement of risk, although VaR has a long history of research, there are few existing researches on the improvement of VaR computing methods. Most of them focus on the study of the application of VaR in various fields. Especially, the research on VaR is relatively late in our country. Many of them are based on the mature research results abroad, from their concepts. Theory, method and empirical research on the use of the VaR method show that few scholars have put forward the framework of VaR calculation method, so that some defects in the risk measurement based on VaR are ignored.VaR method is to estimate the possible maximum loss in the future by statistical analysis of the past income characteristics of financial assets. In the process of calculating VaR, its accuracy depends on the hypothesis of the distribution of the yield of the financial assets studied and the estimation of its variance. This means that the risk measurement method based on VaR has a lack of understanding of the characteristics of the sample data, which will lead to the inaccuracy of the risk measurement and even a larger deviation. The progress and the continuous change in the financial market make the artificial intelligence more and more important in the financial analysis and management, and have aroused the high attention of the scholars. In recent years, the use of deep learning to deal with large data has set off a wave of technological innovation. It has added a powerful tool to quantify the risk of the financial market and broke through the financial risk. The stock market is an important place to predict the development of the future real economy and to mobilize the flow of funds. It is also an important part of the financial market. Because the stock market is not only a place to raise funds, it is also an important channel for public investment in financial management. Stock market shares are used as a voucher for financing and financing. It is closely related to people's economic activities. Moreover, the stock investment itself is also a risk investment. Therefore, the volatility of the stock market can reflect the volatility of the financial risk, and can be used to study the measurement of financial risk. As an example of the stock market, on the basis of the existing literature, in view of the defects existing in the current VaR method, a VaR calculation based on depth learning is proposed. First, the loss in the traditional sense is improved and the expected loss is used, which is more consistent with the diversified definition of the loss in reality. Secondly, the stock return data is set up to be ARCH respectively. The model of the family and a deep artificial neural network model for the expected loss are set up to make a more accurate prediction of the VaR. It is found that the VaR calculation under the depth learning is more accurate than the VaR calculation under the ARCH model. It shows that the VaR calculation based on the depth learning is more practical.
【學(xué)位授予單位】：蘭州財(cái)經(jīng)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：F224;F831

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 余凱;賈磊;陳雨強(qiáng);;深度學(xué)習(xí):推進(jìn)人工智能的夢(mèng)想[J];程序員;2013年06期

2 孫志軍;薛磊;許陽(yáng)明;王正;;深度學(xué)習(xí)研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2012年08期

3 趙曉玲;陳雪蓉;周勇;;金融風(fēng)暴中基于非參估計(jì)VaR和ES方法的風(fēng)險(xiǎn)度量[J];數(shù)理統(tǒng)計(jì)與管理;2012年03期

4 李臘生;孫春花;;VaR估計(jì)中的概率分布設(shè)定風(fēng)險(xiǎn)與改進(jìn)[J];統(tǒng)計(jì)研究;2010年10期

5 陳權(quán)寶;連娟;;對(duì)我國(guó)開(kāi)放式基金風(fēng)險(xiǎn)的實(shí)證研究——基于GARCH模型的VaR方法[J];經(jīng)濟(jì)問(wèn)題;2008年09期

6 劉子斐;史敬;;VaR模型比較技術(shù)及其評(píng)價(jià)——理論、實(shí)證回顧及其應(yīng)用初探[J];金融研究;2008年05期

7 高可佑;王瀟怡;黃勇兵;;滬深300指數(shù)的VaR風(fēng)險(xiǎn)測(cè)量——基于歷史模擬法和蒙特卡羅模擬法[J];市場(chǎng)周刊(理論研究);2008年03期

8 余煒彬;范英;魏一鳴;;基于極值理論的原油市場(chǎng)價(jià)格風(fēng)險(xiǎn)VaR的研究[J];系統(tǒng)工程理論與實(shí)踐;2007年08期

9 王宇新;;GARCH模型和SV模型對(duì)深圳股市的比較[J];合肥工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年06期

10 方毅;張屹山;;CVaR、VaR應(yīng)用在RAROC的比較研究[J];數(shù)理統(tǒng)計(jì)與管理;2007年01期

相關(guān)博士學(xué)位論文 前1條

1 蘇濤;金融市場(chǎng)風(fēng)險(xiǎn)VaR度量方法的改進(jìn)研究[D];天津大學(xué);2007年

相關(guān)碩士學(xué)位論文 前8條

1 李思琴;基于深度學(xué)習(xí)的搜索廣告點(diǎn)擊率預(yù)測(cè)方法研究[D];哈爾濱工業(yè)大學(xué);2015年

2 馬躍;Monte Carlo模擬法在風(fēng)險(xiǎn)度量中的實(shí)證研究[D];中國(guó)礦業(yè)大學(xué);2015年

3 陳先昌;基于卷積神經(jīng)網(wǎng)絡(luò)的深度學(xué)習(xí)算法與應(yīng)用研究[D];浙江工商大學(xué);2014年

4 龔金萍;基于VaR的我國(guó)貨幣市場(chǎng)基金的風(fēng)險(xiǎn)度量及績(jī)效評(píng)價(jià)[D];華東交通大學(xué);2012年

5 毛華富;基于跳躍GARCH模型的VaR風(fēng)險(xiǎn)管理研究[D];西南財(cái)經(jīng)大學(xué);2009年

6 徐永坤;基于隨機(jī)波動(dòng)模型的中國(guó)股市波動(dòng)性實(shí)證研究[D];復(fù)旦大學(xué);2008年

7 曹建美;VaR方法在中國(guó)股票市場(chǎng)風(fēng)險(xiǎn)度量中的應(yīng)用[D];東北財(cái)經(jīng)大學(xué);2007年

8 張紅;基于VAR模型的貨幣市場(chǎng)基金風(fēng)險(xiǎn)管理研究[D];中國(guó)海洋大學(xué);2007年

，

本文編號(hào)：1905360