跳到主要內容

臺灣博碩士論文加值系統

(44.201.99.222) 您好!臺灣時間:2022/12/05 23:19
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:林建瑋
研究生(外文):Jian-Wei Lin
論文名稱:基於量子啟發式禁忌搜尋演算法搜尋出最佳的交易策略
論文名稱(外文):Searching Optimal Trading Strategy based on Quantum-inspired Tabu Search Algorithm
指導教授:周耀新
指導教授(外文):Yao-Hsin Chou
口試委員:郭奕宏游家牧陳麒元
口試委員(外文):I-Hong KuoChia-Mu YuChi-Yuan Chen
口試日期:2015-07-30
學位類別:碩士
校院名稱:國立暨南國際大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:中文
論文頁數:33
中文關鍵詞:擇時量子啟發式禁忌搜尋演算法技術分析滑動視窗
外文關鍵詞:TimingQuantum-inspired Tabu Search algorithmTechnical analysisSliding window
相關次數:
  • 被引用被引用:0
  • 點閱點閱:395
  • 評分評分:
  • 下載下載:23
  • 收藏至我的研究室書目清單書目收藏:0
由於通貨膨脹加上銀行低利率的關係會使得金錢的價值縮水,因此投資就顯得極為重要。因為股票市場的投資報酬率高於其它投資工具,使得它成為金融市場中熱門的標的物。然而股市行情的變化是難以預測的,要如何選擇適當的時機點進行交易是個非常困難的問題。本研究使用技術分析中最常見的價格與成交量,提出全新移動平均線策略的方法,並搭配量子啟發式禁忌搜尋演算法(QTS)的尋優能力,建立一套最佳的擇時交易決策系統。此外,採用滑動視窗的方法,隨時間與環境改變訓練的資料而動態調整交易策略,避免發生過度適應的問題。經實驗結果顯示,不論在近年的台灣股票市場、美國股票市場中本研究方法均可獲得較高的投資報酬率。
The investment is very important, because of inflation, low interest rates lead to reduced value of money. Owing to the return of stock investment is more than other kinds of investment. It became the financial market become more popular in recent years. However, the stock market is uncertain, complicated and difficult to predict. Hence, how to find the proper trading times for stock markets is a difficult problem. In this study, we use technical analysis in the trading price and trading volume, and proposes a new method to calculate the moving average. Owing to Quantum-inspired Tabu Search (QTS) algorithm can search and find the optimal efficiencies, so QTS is used to find the optimal trading time to establish a system of trading decisions. In addition, to avoid the over-fitting problem, we adopt the sliding window to dynamically adjust trading strategies with training data over time. The results show that the proposed method to overcome some situations, such as Taiwan stock market, US stock market. Consequently, the proposed approach having much more returns of investment (ROI) than other schemes.
目次
誌謝 I
摘要 II
Abstract III
目次 IV
圖目次 V
表目次 VI
第一章、緒論 1
1.1、簡介 1
1.2、研究背景 3
1.2.1、台灣股票市場 3
1.2.2、技術分析 4
1.2.3、移動平均線( Moving Average, MA ) 5
第二章、文獻探討 6
第三章、研究方法 8
3.1、改良式移動平均線 9
3.2、滑動視窗 10
3.3、量子啟發式禁忌搜尋演算法 11
3.3.1、Encoding 11
3.3.2、Initialize quantum matrix 12
3.3.3、Measure quantum matrix 12
3.3.4、Evaluate the fitness function 13
3.3.5、Update quantum matrix 14
3.3.6、Strategy of twice train 15
第四章、實驗結果 16
4.1、實驗標的0050ETF 16
4.2、實驗環境 18
4.3、實驗結果與分析 19
4.4、加入成交量的判斷 27
4.5、個股實驗 28
第五章、結論與未來目標 30
References 31

圖目次
圖 1技術分析理論 4
圖 2移動平均線的買進及賣出時機 5
圖 3滑動視窗 10
圖 4演算法流程圖 11
圖 5編碼介紹 11
圖 6量子陣列 12
圖 7初始量子陣列 12
圖 8隨機亂數值 12
圖 9測量後的交易策略 12
圖 10適應值 14
圖 11最佳與最差策略的差異 14
圖 12更新量子陣列 14
圖 13訓練期交易示意圖 15
圖 14當ETF溢價時套利示意圖 17
圖 15傳統方法中表現最好的策略 19
圖 16本研究改良的方法及選到的買賣策略 19
圖 17傳統與本研究方法結果比較(平盤) 20
圖 18傳統方法中表現最好的策略 21
圖 19本研究改良的方法及選到的買賣策略 21
圖 20傳統與本研究方法結果比較(上漲) 22
圖 21傳統方法中表現最好的策略 22
圖 22本研究改良的方法及選到的買賣策略 23
圖 23傳統與本研究方法結果比較(下跌) 23
圖 24訓練期2010年到2013年實驗結果 24
圖 25訓練期2013年到2014年實驗結果 24
圖 26測試期2010年到2013年結果 25
圖 27測試期2013年到2014年結果 25
圖 28加入成交量判斷的四種方法與結果 27
圖 29兩種方法的實驗結果比較 27
圖 30台積電(2013/1-2015/6)實驗結果 28
圖 31華碩(2013/1-2015/6)實驗結果 28
圖 32宏達電(2013/1-2015/6)實驗結果 28
圖 33 0050ETF(2015/1-2015/6實驗結果) 29

表目次
表 1傳統與本研究提出的方法比較表 9
表 2交易系統的參數設定 18
表 3美國股市中不同指數的實驗結果 26
[1]Y. H. Chou, Y. J. Yang, and C. H. Chiu, “Classical and quantum-inspired Tabu search for solving 0/1 knapsack problem”, Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on, pp.1364-1369, 2011.
[2]Y. H. Chou, S. Y. Kuo, W. L. Chang, Y. J. Yang, W. H. Wang, C. H. Chiu, and S. F. Huang, “Quantum-Inspired Tabu Search Algorithm for Reversible Logic Circuit Synthesis”, Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on, pp.709-714, 2012.
[3]H. P. Chiang, Y. H. Chou, C. H. Chiu, S. Y. Kuo, and Y. M. Huang, “A quantum-inspired Tabu search algorithm for solving combinatorial optimization problems”, Soft Computing, pp.1-11, 2013.
[4]E. Hurwitz, and T. Marwala, “Suitability of using technical indicator-based Strategies as potential strategies within intelligent trading systems”, Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on, pp.80-84, 2011.
[5]P. C. Chang, T. W. Liao, F. C. Lin, and J. J. Lin, “A dynamic threshold decision system for stock trading signal detection”, Applied Soft Computing 11, pp.3998–4010, 2011.
[6]F. H. Westerhoff, “Technical analysis based on price-volume signals and the power of trading breaks”, International Journal of Theoretical and Applied Finance 9, pp.227–244, 2006.
[7]L. A. Teixeira, and A. L. Oliveira, “Predicting stock trends through technical analysis and nearest neighbor classification”, Systems, Man and Cybernetics (SMC), 2009 IEEE International Conference on, pp.3094-3099, 2009.
[8]F. Allen, and R. Karjalainen, “Using genetic algorithms to find technical trading rules,” Journal of Financial Economics, vol.51, no.2, pp.245-271, 1999.
[9]N. Jiarui, and C. Zhang, “Mining Better Technical Trading Strategies with Genetic Algorithms”, Integrating AI and Data Mining (AIDM), International Workshop on, pp.26-33, 2006.
[10]L. A. Becker, and M. Seshadri, “GP-evolved technical trading rules can outperform buy and hold”, In Proc. 6th Intl Conf. on Computational Intelligence and Natural Computing, North Carolina USA, 2003.
[11]A. C. Briza, and P. C. Naval Jr., “Stock trading system based on the multi-objective particle swarm optimization of technical indicators on end-of-day market data,” Applied Soft Computing Journal, vol.11, no.1, pp.1191-1201, 2011.
[12]R. C. Brasileiro, V. L. F. Souza, B. J. T. Fernandes, and A. L. I. Oliveira, “Automatic method for stock trading combining technical analysis and the Artificial Bee Colony Algorithm”, Evolutionary Computation (CEC), 2013 IEEE Congress on, pp.1810-1817, 2013.
[13]A. Garliauskas, “Neural network chaos and computational algorithms of forecast in finance”, Systems, Man, and Cybernetics, 1999 IEEE International Conference on , vol.2, pp.638-643, 1999.
[14]N. Kourentzes, and F. Crone, “Frequency independent automatic input variable selection for Neural Networks for forecasting”, Neural Networks (IJCNN), The 2010 International Joint Conference on, pp.1-8, 2010.
[15]E. W. Saad, D. V. Prokhorov, and D. C. Wunsch, “Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks”, Neural Networks, IEEE Transactions on, vol.9, no.6, pp.1456-1470, 1998.
[16]I. H. Kuo, S. J. Horng, T. W. Kao, T. L. Lin, C. L. Lee, and Y. Pan, “An improved method for forecasting enrollments based on fuzzy time series and particle swarm optimization”, Expert Systems with Applications, pp.6108–6117, 2009.
[17]A. Hirabayashi, C. Aranha, and H. Iba, “Optimization of the Trading Rule in Foreign Exchange using Genetic Algorithm”, In Proceedings of GECCO 2009, pp.1529-1536, ACM press, 2009.
[18]J. H. Wang, S. M. Chen, and J. Y. Leu, “Stock trading decision support system using a rule selector based on sliding window”, Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation, 1997 IEEE International Conference on, vol.1, pp.559-564, 1997.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊