研究生: |
賴佳君 Chia-chun Lai |
---|---|
論文名稱: |
應用平滑支撐向量機於台指期貨套利之研究 An Application of Smooth Support Vector Machines on Taiwan Stock Index Futures Arbitrage |
指導教授: |
余尚武
Shang-Wu Yu |
口試委員: |
薛明玲
none 張光第 none |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 資訊管理系 Department of Information Management |
論文出版年: | 2006 |
畢業學年度: | 94 |
語文別: | 中文 |
論文頁數: | 97 |
中文關鍵詞: | 台灣50指數ETF 、持有成本理論 、預期理論 、平滑支撐向量機 |
外文關鍵詞: | Taiwan Top 50 Tracker Fund (TTT), expectation theory, cost-of-carry model, smooth support vector machines (SSVM |
相關次數: | 點閱:313 下載:2 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
以往文獻指出套利時點具有持續存在的現象,但在套利者資金部位有限的情況下,如何選擇出較佳之進場套利時點,將資金部位做出有效的運用,以達到最穩定優質之套利報酬乃為本研究之目的。
本研究結合持有成本理論與預期理論於套利策略中,首先以持有成本理論建構無套利區間,發掘出可行套利時點,再以預期理論為基底,預測下一點基差走勢來決定進場時點以輔助套利者鎖定較佳的套利報酬。在預測工具的選擇上,則採用近年來於分類、預測領域表現傑出,卻尚未被應用於套利實證研究之平滑支撐向量機(SSVMs)作為本研究之預測工具。
研究樣本取樣期間為2005年9月22日至2006年3月15日之日內分鐘資料,以買入最高價、賣出最低價的方式來建構「期貨與TTT」之套利模型,並另建構「期貨與現貨」之交易稅為0.3%及0.1%情境下的套利模型,以利研究對照。經實證研究後,本研究發現:
一、 「期貨與現貨」之套利機會已很少發生,若交易稅降低將得以顯著提升套利機會。在「期貨與TTT」之套利模型中,因TTT挾有交易稅低之優勢,使其擁有較多套利機會。
二、 在任一套利模型中,有使用預測工具之平均獲利報酬皆高於不使用預測工具,顯示運用基差擇時策略對於套利者而言,具有實質助益。
三、 在預測工具方面,SSVR較SSVM之預測準確度高出10~20%,於任一套利模型中之平均獲利報酬亦呈現較穩定優質的表現,顯示SSVR相當適合應用於套利預測模型。
四、 以TTT來取代現貨部位可鎖住較大的套利空間,但其最大可能損失點數之標準差超過合理範圍,顯示單純用TTT來複製台股指數之潛在風險極高,容易因模擬誤差的突然變大或縮小而侵蝕利潤。
In the literatures, many studies address that arbitrage opportunities have the phenomenon of continuous existence. However, fund position of arbitrageurs is limited and the purpose of the thesis is that choosing the better arbitrage opportunities in the market and applying fund position effectively to achieve optimal performance of arbitrage.
Our research proposes an arbitrage strategy which combines cost-of-carry model with expectation theory. First, we use cost-of-carry model to construct “no-arbitrage-boundaries” and discover the timing of arbitrage. Second, through the expectation theory, the next basis tendency is predicted to determine the time of entering the market which can assist arbitrageurs lock better arbitrage performance. Additionally, for choosing prediction tools, we adopt smooth support vector machines (SSVMs). SSVMs outstand for classification and prediction in recent years, but it has not been applied to arbitrage studying yet.
The periods of the sample selection are the intraday data from September 22, 2005 to March 15, 2006. The arbitrage model of “futures versus TTT” is constructed by the way of buying in the highest price and selling the bottom price. The arbitrage model of “futures versus spot” is also constructed to be the comparison with securities transactions tax 0.3% and 0.1%. The findings are as follows.
1. The arbitrage opportunities of futures versus spot seldom happen. If the sales tax of 「futures versus spot」 is decreased, the arbitrage opportunities will increase significantly. Because TTT has the advantage of lower sales tax in the arbitrage model of「futures versus TTT」, it has more arbitrage opportunities.
2. For any model of arbitrage, the average rate of return with predicting tools is higher than that without predicting tools. It is helpful for arbitrageurs to apply the strategy of basis time selection.
3. From the perspective of predicting tools, the accuracy of SSVR is 10 to 20% higher than the result of SSVM. In addition, the average rate of return of SSVR is excellent in any arbitrage model. Hence, SSVR is proper for being applied to arbitrage prediction models.
4. We can lock greater arbitrage space using TTT to replace spot; however, the standard deviation of the greatest possible loss points of TTT exceeds the rational ranges. The risk is quiet high to reproduce spot using TTT purely, because the profit is easily eroded due to that the tracking error becomes large or small suddenly.
中文部份
[1] 卞志祥 (1996),「台灣加權股價指數投資組合之基因演算法建構模型」,國立交通大學資訊管理研究所碩士論文。
[2] 王金火 (2001),指數期貨套利在台灣股票及期貨巿場之獲利性-事前分析日內資料,國立成功大學會計學研究所碩士論文。
[3] 李凌均 (2004),「基於支持向量機的機械設備狀態趨勢預測研究」,西安交通大學學報,第38卷第3期,230-234頁。
[4] 李存修 (2004),「ETF套利研究」,高盛(亞洲)有限公司課題研究。
[5] 姒元忠、林堯琦 (1997),「攻戰台股指數期貨」,金錢文化出版。
[6] 林文政、臧大年 (1996),「台灣股指期貨定價與套利實務問題探討」, 證券市場發展季刊,第8卷第3期,1-31頁。
[7] 紀朝介 (2004),「ETFs應用於台股期貨之套利研究」,淡江大學管理科學研究所碩士論文。
[8] 徐俊明,「投資學理論與實務」,新陸書局。
[9] 徐美珍 (2003),「企業財務危機之預測」,國立政治大學統計研究所碩士論文。
[10] 翁許細 (1994),「指數基金特性與設計方式之研究-以台灣為例」,國立台灣大學財務金融研究所碩士論文。
[11] 許順發 (1999),「台股指數期貨套利策略之實證研究--以TAIFEX為例」,大葉大學事業經營研究所碩士論文。
[12] 陳松男 (1996),「選擇權與期貨:衍生性商品」,三民書局。
[13] 陳啟斌 (1999),「台灣加權指數期貨之套利實證」,國立臺灣大學國際企業研究所碩士論文。
[14] 陳雅雯 (2002),「支援向量機於預測臺灣股市股價漲跌之實證研究」,南華大學資訊管理學研究所碩士論文。
[15] 陳展維 (2004),「基於平滑支撐向量機之電腦病毒偵測系統」,國立台灣科技大學資訊工程系碩士論文。
[16] 彭志弘 (1999),「台灣股價指數期貨套利之相關研究」,國立政治大學金融學研究所碩士論文。
[17] 黃銘煌 (1999),「TAIFEX 與SIMEX 台股指數期貨跨市場價差交易策略之研究」,國立台灣大學商學研究所碩士論文。
[18] 黃雅蘭 (2001),「台灣股價指數期貨套利之研究-類神經網路與灰色理論之應用」,國立台灣科技大學資訊管理系碩士論文。
[19] 黃建銘 (2005),「支撐向量機的自動參數選擇」,國立台灣科技大學資訊工程系碩士論文。
[20] 葉明政 (2004),「應用遺傳演化模糊類神經網路於指數期貨套利之研究」,東吳大學經濟學系碩士論文。
[21] 劉舜田 (1999),「TAIMEX台股指數期貨之定價、套利與預測」,國立成功大學企業管理學系碩士論文。
[22] 劉易昌 (2003),「支援向量機於財務預測上之應用」,靜宜大學資訊管理學系碩士論文。
[23] 歐宏杰、賴朝隆、劉宗聖(2003),「台灣50指數ETF投資實務」,秀威資訊科技。
[24] 賴建順 (2003),「台灣50股價指數期貨套利之實證研究」,嶺東技術學院財務金融研究所碩士論文。
[25] 錢明華 (2004),「台灣股價指數期貨套利的替代方法─利用分類股價指數期貨及ETF」,國立台灣科技大學財務金融研究所碩士論文。
[26] 繆文娟 (1999),「摩根台股指數期貨套利策略之研究」,國立政治大學財務管理學系碩士論文。
[27] 鍾秀培 (1997),「運用類神經網路建構指數套利模型-以日經225指數為例」,國立交通大學資訊管理研究所碩士論文。
[28] 鍾益仔 (2001),「台灣期貨交易所股價指數期貨套利性之實證研究」,國立中正大學企業管理研究所碩士論文。
英文部份
[1] Brenner, M.,M.G. Subrahmanyam and J. Uno (1989), “The Behavior of Prices in the Nikkei Spot and Futures Market,” Journal of Financial Economics, Vol.23, No.2, pp.363-383
[2] Bisse, Stephan (2005), “Weight+Volume+Move-Adjusted Moving Average:It’s WEVOMO!,” Technical Analysis of Stocks & Commodities, Vol.23:April, pp.32-35
[3] Cornell, B. and K.R. French (1983), “The Pricing of Stock Index Futures,” Journal of Futures Markets, Vol.3, No.1, pp.1-14
[4] Cao, D.-Z., Pang, S.-L., Bai, Y.-H. (2005), ”Forecasting exchange rate using support vector machines,” 2005 International Conference on Machine Learning and Cybernetics, pp. 3448-3452
[5] Fremault, A. (1991), “Stock Index Futures and Index Arbitrage in a Rational Expectations Model,” Journal of Business, Vol.64, No.4, pp.523-547.
[6] Figlewski, S. (1984), “Hedging Performance and Basis Risk in Stock Index Futures,” Journal of Finance, Vol.39, No.3, pp.657-670
[7] Fan, A., Palaniswami, M. (2001), ”Stock selection using support vector machines,” Proceedings of the International Joint Conference on Neural Networks 3, pp.1793-1798
[8] Hsu, Chih-Wei, Chang, Chih-Chung, and Lin, Chih-Jen. (2003), “A Practical Guide to Support Vector Classification”, Available at http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[9] Klemkosky, R.C. and J.H. Lee (1991), “The Intraday Ex Post and Ex Ante Profitability of Index Arbitrage,” Journal of Futures Markets, Vol.11, No.3, pp.291-311
[10] Kim, K.-J. (2003), ”Financial time series forecasting using support vector machines,” Neurocomputing 55 (1-2), pp. 307-319
[11] Lee, Y.-J., Mangasarian, O.L. (2001), ”SSVM:A Smooth Support Vector Machine for Classification,” IEEE Transactions on Knowledge and Data Engineering 17 (5), pp. 678-685.
[12] Lee, Y.-J., Hsieh, W.-F., Huang, C.-M. (2005), ”ε-SSVR: A smooth support vector machine for ε-insensitive regression,”, IEEE Transactions on Knowledge and Data Engineering 17 (5), pp. 678-685
[13] Meade N. and G. R. Salkin (1989), "Index Fund-Construction and Performance Measurement,” Journal of Operational Research Society, Vol.40 ,No.10,pp.871-8
[14] Modest, D.M. and M. Sundaresan (1983), “The Relationship Between Spot and Futures Prices in Stock Index Futures Markets: Some Preliminary Evidence,” Journal of Futures Markets, Vol.3, No.1, pp.15-41
[15] Miller (1990), “Index Arbitrage and volatility”, Financial Analysts Journal, Vol.46, No.4, pp.6-7
[16] Rudd, A. (1980), "Optimal Selection of Passive Portfolio,” Financial Management, Spring, pp.57-66
[17] Saunders and Mahajan (1988), “An Empirical Examination of Composite Stock Index Futures Pricing,” Journal of Futures Markets, Vol.8, No.2, pp.211-228
[18] V. Vapnik, (1995) ”The Nature of Statistical Learning Theory,” Springer Verlan, New York.
[19] Wang, D., Wu, W.-F. (2003), “Application of support vector machines regression in prediction Shanghai stock composite index,” Wuhan University Journal of Natural Sciences 8 (4), pp. 1126-1130
[20] Yau, J., Schneeweis T., and Yung K. (1990), “The Behaviour of Stock Index Futures Prices in Hong Kong: Before and After the Crash,” Pacific Basin Capital Market Research, pp.357-378