本文選題：新華富時A50股指期貨　切入點(diǎn)：極限學(xué)習(xí)機(jī)　出處：《深圳大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：新華富時A50股指期貨是在中國境外上市以中國A股市場股票為標(biāo)的金融衍生品。同國內(nèi)的指數(shù)期貨相比具有較低的交易成本、高杠桿、高流通性等特點(diǎn),是金融活動參與者進(jìn)行風(fēng)險管理及投資的重要金融工具。由于A50股指期貨受多種復(fù)雜因素的影響,以及時間序列自身非線性、動態(tài)、高噪聲等特性,運(yùn)用傳統(tǒng)金融時間序列研究方法無法逼近其內(nèi)在運(yùn)動規(guī)律,隨著計算機(jī)科學(xué)、人工智能、大數(shù)據(jù)的發(fā)展,基于統(tǒng)計理論的機(jī)器學(xué)習(xí)算法廣泛應(yīng)用到時間序列的分析中并取得顯著成效。本文主要目的是研究極限學(xué)習(xí)機(jī)在新華富時A50股指期貨交易中的應(yīng)用,由于極限學(xué)習(xí)機(jī)具有良好的非線性逼近能力、運(yùn)算速度快、結(jié)構(gòu)簡單等特點(diǎn),因此本文選用極限學(xué)習(xí)機(jī)為主要建模工具,本文樣本數(shù)據(jù)為2013年7月26日至2016年9月23日期間的775個交易日的A50期貨指數(shù)收盤價數(shù)據(jù),其中前600個數(shù)據(jù)作為訓(xùn)練集,后175個數(shù)據(jù)為預(yù)測集。為了進(jìn)行比較,本文選取四個投機(jī)策略(A1至A4)和兩個對沖策略(B1和B2)進(jìn)行計算和分析,其中A1和A2為一般的根據(jù)趨勢技術(shù)指標(biāo)進(jìn)行的交易策略,A3和A4為根據(jù)極限學(xué)習(xí)機(jī)結(jié)果進(jìn)行的交易策略。B1為根據(jù)一般對沖原則的交易策略,B2為根據(jù)模型結(jié)果進(jìn)行波段操作的交易策略(具體說明見正文)。由于支持向量機(jī)也有廣泛的應(yīng)用,本文還選取支持向量機(jī)作為參照模型進(jìn)行計算和比較。研究發(fā)現(xiàn):(1)極限學(xué)習(xí)機(jī)在模型的結(jié)構(gòu)、學(xué)習(xí)能力、預(yù)測精度等方面都要優(yōu)于高斯核支持向量機(jī)。極限學(xué)習(xí)機(jī)模型的平方根均方誤差、正則均方誤差、平均絕對誤差均小于高斯核支持向量機(jī)模型的對應(yīng)誤差。(2)極限學(xué)習(xí)機(jī)由于自身網(wǎng)絡(luò)結(jié)構(gòu)簡單、運(yùn)算速度快、泛化能力強(qiáng)等特點(diǎn),較好的逼近新華富時A50股指期貨每日收盤價的走勢。預(yù)測值與實(shí)際值的誤差最大相差0.5點(diǎn)。精準(zhǔn)的預(yù)測有利于提高交易策略的勝率、盈利空間,同時降低價格波動帶來的風(fēng)險。(3)實(shí)證結(jié)果表明:無論是投機(jī)策略還是對沖策略,根據(jù)極限學(xué)習(xí)機(jī)模型結(jié)果建立的交易策略均優(yōu)于其它交易策略,前者不僅能夠有起到風(fēng)險預(yù)警作用,還能大幅提高收益。在預(yù)測集中,四種投機(jī)策略收益率分別為21.84%、24.16%、140.79%、62.80%。其中A3策略的收益率分別是A1、A2策略的6.4、5.8倍。A4策略的收益率分別A1、A2策略的2.9、2.6倍,在對沖策略中,依據(jù)極限學(xué)習(xí)機(jī)模型結(jié)果的對沖策略B2的收益率是B1(依據(jù)一般對沖原則)7.1倍。由此可見,根據(jù)極限學(xué)習(xí)機(jī)模型結(jié)果而采取的交易策略有顯著優(yōu)勢。
[Abstract]:Xinhua FTSE A50 stock index futures are financial derivatives listed outside China with Chinese A-share market shares. Compared with domestic index futures, they have the characteristics of low transaction cost, high leverage, high liquidity, etc. A50 stock index futures are influenced by many complicated factors, and the time series are nonlinear, dynamic, high noise and so on. With the development of computer science, artificial intelligence and big data, the traditional financial time series research method can not approach its internal motion law. The machine learning algorithm based on statistical theory is widely used in the analysis of time series and has achieved remarkable results. The main purpose of this paper is to study the application of extreme learning machine in the trading of stock index futures of Xinhua FTSE A50. Because extreme learning machine has good nonlinear approximation ability, fast operation speed, simple structure and so on, this paper chooses the ultimate learning machine as the main modeling tool. The sample data in this paper are A50 futures index closing price data for 775 trading days from July 26th 2013 to September 23rd 2016, of which the first 600 data are training sets and the last 175 data are forecast sets. In this paper, four speculative strategies (A1 to A4) and two hedging strategies (B _ 1 and B _ 2) are selected for calculation and analysis. Where A1 and A2 are general trading strategies based on trend technical indicators. A3 and A4 are trading strategies based on extreme learning machine results. B1 is trading strategy based on general hedging principle. Trading strategies for segment operations (see text for details.) because support vector machines are also widely used, This paper also selects support vector machine as the reference model to calculate and compare the structure and learning ability of the ultimate learning machine. The prediction accuracy is better than that of Gao Si kernel support vector machine. The square root mean square error, regular mean square error of extreme learning machine model, The average absolute error is smaller than the corresponding error of Gao Si kernel support vector machine model. Better approach to the trend of the daily closing price of the Xinhua FTSE A50 stock index futures. The biggest difference between the predicted value and the actual value is 0.5 points. Accurate prediction is helpful to improve the winning rate of trading strategy and profit space. The empirical results show that both speculative and hedging strategies are superior to other trading strategies based on the results of extreme learning machine model. The former can not only serve as a warning of risks, but also significantly increase returns. The return rate of the four speculative strategies is 21.84 / 24.16 / 140.79 / 62.80 respectively. The yield of A3 strategy is 6.4or 5.8 times that of A1A _ 2 strategy. The return rate of A4 strategy is 2.9or 2.6 times that of A _ 1 / A _ 2 strategy, respectively. The yield of the hedging strategy B2 based on the LLM model is 7.1 times that of B1 (according to the general hedging principle). It can be seen that the trading strategy based on the LLM model has significant advantages.
【學(xué)位授予單位】：深圳大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：F724.5

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 逯向軍;;解讀:華富集團(tuán)總裁陳啟建的豪宅情結(jié)[J];甘肅金融;2006年01期

2 ;華富基金:耐心等待底部的到來[J];股市動態(tài)分析;2011年23期

3 徐大龍;真人俞華富[J];光彩;2001年04期

4 ;騰飛中的華富[J];人大研究;2002年Z1期

5 綦敏;全行業(yè)共同的企盼——承德華富玻璃藝術(shù)館開業(yè)慶典[J];玻璃與搪瓷;2005年05期

6 鄒震;;關(guān)于中國開源發(fā)展源動力的思考[J];程序員;2005年11期

7 ;天華富邦公司被評為省高新技術(shù)企業(yè)[J];瀘州科技;2008年02期

8 余海峰;;“華富”和膠體電池“共同成長”[J];中國自行車;2009年06期

9 周壽斌;王君俐;;華富:創(chuàng)新推動精彩轉(zhuǎn)型[J];中國自行車;2009年10期

10 趙迪;;富國匯利、華富強(qiáng)化一日售罄 資金涌入債券基金 風(fēng)險抑或機(jī)遇[J];股市動態(tài)分析;2010年36期

相關(guān)重要報紙文章 前10條

1 路建青 孫存德;華富，這樣創(chuàng)造傳奇[N];蘭州日報;2004年

2 本報記者 王繼高;曾剛“黯然”離職 華富基金雪上加霜[N];中國經(jīng)濟(jì)時報;2011年

3 記者 鑫平;新華富時推出復(fù)合指數(shù)[N];中國證券報;2003年

4 本版撰文 逯向軍;觸摸誠意的細(xì)節(jié)[N];蘭州日報;2005年

5 本報記者　　　王軍;新華富時指數(shù)變更[N];中國證券報;2006年

6 王軍;新華富時推出H股指數(shù)[N];中國證券報;2006年

7 王軍;中國人壽快速納入新華富時指數(shù)[N];中國證券報;2007年

8 余U，

本文編號：1587770