一个基于技术指标规则的启发式量化择时系统
|
摘要
设计了一个新型的基于技术指标规则的启发式量化择时系统(TIR-HA),通过模拟退火算法从大量技术指标规则中选取优化的规则组合,并利用一个改进的多数投票方法将所选规则的信号综合,可以在深入挖掘大量指标规则择时能力的同时综合考虑指标的超前性、滞后性以及在不同时间段的预测能力。本文将该系统应用于中国股票市场沪深300指数成分股116只股票的日交易数据,实证结果显示算法的夏普比率、索提诺比率、择时准确率和单次交易平均年化收益率均显著高于多数投票组合规则择时策略和基于机器学习预测的择时策略。
This paper designs a novel heuristic system, TIR-HA, using simulated annealing to select the optimized combinations from a large number of technical indicator rules, and incorporating an adjusted voting method to combine the trading signals of selected rules. It takes into account of the leading and lagging characteristic of indicator rules while deeply mines the timing capacity of the combined ones. The TIR-HA system is then applied to the daily trading data of 116 component stocks of Chinese CSI300 index. The empirical results show that the Sharpe ratio sortino ratio timing accuracy and average annually return per trading of TIR-HA are significantly higher than the performance of timing strategies that based on majority voting and machine learning algorithms.
This paper designs a novel heuristic system, TIR-HA, using simulated annealing to select the optimized combinations from a large number of technical indicator rules, and incorporating an adjusted voting method to combine the trading signals of selected rules. It takes into account of the leading and lagging characteristic of indicator rules while deeply mines the timing capacity of the combined ones. The TIR-HA system is then applied to the daily trading data of 116 component stocks of Chinese CSI300 index. The empirical results show that the Sharpe ratio sortino ratio timing accuracy and average annually return per trading of TIR-HA are significantly higher than the performance of timing strategies that based on majority voting and machine learning algorithms.
引文
[1] Metghalchi M,Marcucci J,Chang Y H.Are moving average trading rules profitable?Evidence from the European stock markets.Applied Economics,2012,44(12):1539-1559.
[2] Chiang Y C,Ke M C,Liao T L,Wang,C D.Are technical trading strategies still profitable?Evidence from the Taiwan Stock Index Futures Market.Applied Financial Economics,2012,22(12),955-965.
[3] Mendens L,Codinho P,Dias J.A Forex trading system based on a genetic algorithm [J].Journal of Heuristics,2012,18:627-656.
[4] 林文修,蔡秉洲.集成基因表达规划法应用于动态股票交易策略探勘之研究[J].中国管理科学,2015,23(S1):510-517.
[5] 李斌,林彦,唐闻轩.ML-TEA:一套基于机器学习和技术分析的量化投资算法[J].系统工程理论与实践,2017,37(5):1089-1100.
[6] Patel J,Shah S,Thakkar P,et al.Predicting stock market index using fusion of machine learning techniques [J].Expert Systems with Applications,2015,42:2162-2172.
[7] Gunduz H,Yaslan Y,Cataltepe Z.Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations [J].Knowledge-Based Systems,2017,137:138-148.
[8] Haefke C,Helmenstein C.Predicting stock market averages to enhance profitable trading strategies [C].In Proceedings of the third international conference on neural networks in the capital markets,2000,London,378-389.
[9] Lai R K,Fan C,Huang W,et al.Evolving and clustering fuzzy decision tree for financial time series data forecasting [J].Expert Systems with Applications,2009,36:3761-3773.
[10] Hu Y,Liu K,Zhang X,et al.Application of evolutionary computation for rule discovery in stock algorithmic trading:a literature review [J].Applied Soft Computing,2015,36:534-551.
[11] Allen F,Karjalainen R.Using genetic algorithms to find technical trading rules.Journal of Financial Economics,1999,51(2):245-271.
[12] Briza A,Naval P Jr.Stock trading system based on the multi-objective particle swarm optimization of technical indicators on end-of-day market data [J].Applied Soft Computing,2011,11(1),1191-1201.
[13] Wang F,Yu P L H,Cheung D W,Combining technical trading rules using particle swarm optimization [J].Expert Systems with Applications,2014,41:3016-3026.
[14] Chen Y,Mabua S,Shimadab K,et al.A genetic network programming with learning approach for enhanced stock trading model [J].Expert Systems with Applications,2009,36:12537-12546.
[15] Mabu S,Hirasawa K,Obayashi M,et al.Enhanced decision making mechanism of rule-based genetic network programming for creating stock trading signals [J].Expert Systems with Applications,2013,40:6311-6320.
[16] Esfahanipour A,Mousavi S.A genetic programming model to generate risk-adjusted technical trading rules in stock markets [J].Expert Systems with Applications,2011,38:8438-8445.
[17] Ozturk M,Toroslu I H,Fidan G.Heuristic based trading system on Forex data using technical indicator rules [J].Applied Soft Computing,2016,43:170-186.
[18] Kim Y,Ahn W,Oh K J,et al.An intelligent hybrid trading system for discovering trading rules for the futures market using rough sets and genetic algorithms [J].Applied Soft Computing,2017,55:127-140.
[19] 刘宇霞.组合指标个股量化择时交易的实证研究 [J].科技创业月刊,2015,12:19-79.
[20] 丁鹏.量化投资——策略与技术 [M].北京:电子工业出版社,2012.
[21] 梁淇俊,郑贵俊,徐守萍.基于生存分析的择时策略择优体系研究——以技术指标交易信号为例 [J].金融经济学研究,2015,30(1):96-106.
[22] Zhang X Z,Hu Y,Xie K,et al.An evolutionary trend reversion model for stock trading rule discovery [J].Knowledge Based Systems,2015,79:27-35.
[23] Hu Y,Feng B,Zhang X Z,et al.Stock trading rule discovery with an evolutionary trend following model.Expert Systems with Application,2015,42(1):212-222.
[24] 王丝丝,张敬磊,陈慈,张洪宾,马春杰.基于方差与改进群智能算法的K-means聚类优化[J].系统科学与数学,2018,38(10):1117-1127.
[25] 李汉东,张吟,张瑞.基于联合违约概率的资产组合投资优化方法[J].系统工程理论与实践,2018,38(03):556-564.
[26] Arts E,Korst J.Simulated annealing and Boltzmann machines [M].New York:Wiley,1989.
[27] 陈荣达,虞欢欢.基于启发式算法的支持向量机选股模型.系统工程,2014,32(2):40-48.
[28] 黄连忠,万晓跃,孙永刚,王寰宇,王壮.基于模拟退火算法的船舶航速优化研究.船舶,2018,S1:8-17.
[29] Metropolis N,Rosenbluth A W,Rosenbluth M N,Teller A H.Equation of State Calculations by Fast Computing Machines.The Journal of Chemical Physics,1953,21(6):1087-1092.
[30] Kirpatrick S,Gelatt C D,Vecchi M P.Optimization by simulated annealing.Science,1983,220(4598):671-680.
[31] 曹引,冶运涛,梁犁丽,蒋云钟,赵红莉,王浩.高山流域降水无线传感器网络节点布局优化方法[J].系统工程理论与实践,2018,38(8),2168-2176.
[32] 王诺,田玺环,吴迪,吴暖.基于陆海协同的海上战略投送选址——路径优化.系统工程理论与实践,2018,38(11),2929-2941.
[33] Isakov S V,Zintchenko I N,R?nnow T F,Troyer M.Optimised simulated annealing for Ising spin glasses.Computer Physics Communications,2015,192,265-271.
[34] Lyden S,Haque M E.A Simulated Annealing Global Maximum Power Point Tracking Approach for PV Modules Under Partial Shading Conditions.IEEE Transactions on Power Electronics,2016,31(6):4171-4181.
[35] Luo L K,You S Y,Xu Y R,et al.Improving the integration of piece wise linear representation and weighted support vector machine for stock trading signal prediction.Applied Soft Computing,2017,56:199-216.
[36] Duran A,Bommarito M J.A profitable trading and risk management strategy despite transaction costs [J].Quantitative Finance,2011,11(6):829-848.
[37] Lai R K,Fan C,Huang W,et al.Evolving and clustering fuzzy decision tree for financial time series data forecasting [J].Expert Systems with Applications,2009,36:3761-3773.
[38] Hu Y,Liu K,Zhang X,et al.Application of evolutionary computation for rule discovery in stock algorithmic trading:a literature review [J].Applied Soft Computing,2015,36:534-551.
[2] Chiang Y C,Ke M C,Liao T L,Wang,C D.Are technical trading strategies still profitable?Evidence from the Taiwan Stock Index Futures Market.Applied Financial Economics,2012,22(12),955-965.
[3] Mendens L,Codinho P,Dias J.A Forex trading system based on a genetic algorithm [J].Journal of Heuristics,2012,18:627-656.
[4] 林文修,蔡秉洲.集成基因表达规划法应用于动态股票交易策略探勘之研究[J].中国管理科学,2015,23(S1):510-517.
[5] 李斌,林彦,唐闻轩.ML-TEA:一套基于机器学习和技术分析的量化投资算法[J].系统工程理论与实践,2017,37(5):1089-1100.
[6] Patel J,Shah S,Thakkar P,et al.Predicting stock market index using fusion of machine learning techniques [J].Expert Systems with Applications,2015,42:2162-2172.
[7] Gunduz H,Yaslan Y,Cataltepe Z.Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations [J].Knowledge-Based Systems,2017,137:138-148.
[8] Haefke C,Helmenstein C.Predicting stock market averages to enhance profitable trading strategies [C].In Proceedings of the third international conference on neural networks in the capital markets,2000,London,378-389.
[9] Lai R K,Fan C,Huang W,et al.Evolving and clustering fuzzy decision tree for financial time series data forecasting [J].Expert Systems with Applications,2009,36:3761-3773.
[10] Hu Y,Liu K,Zhang X,et al.Application of evolutionary computation for rule discovery in stock algorithmic trading:a literature review [J].Applied Soft Computing,2015,36:534-551.
[11] Allen F,Karjalainen R.Using genetic algorithms to find technical trading rules.Journal of Financial Economics,1999,51(2):245-271.
[12] Briza A,Naval P Jr.Stock trading system based on the multi-objective particle swarm optimization of technical indicators on end-of-day market data [J].Applied Soft Computing,2011,11(1),1191-1201.
[13] Wang F,Yu P L H,Cheung D W,Combining technical trading rules using particle swarm optimization [J].Expert Systems with Applications,2014,41:3016-3026.
[14] Chen Y,Mabua S,Shimadab K,et al.A genetic network programming with learning approach for enhanced stock trading model [J].Expert Systems with Applications,2009,36:12537-12546.
[15] Mabu S,Hirasawa K,Obayashi M,et al.Enhanced decision making mechanism of rule-based genetic network programming for creating stock trading signals [J].Expert Systems with Applications,2013,40:6311-6320.
[16] Esfahanipour A,Mousavi S.A genetic programming model to generate risk-adjusted technical trading rules in stock markets [J].Expert Systems with Applications,2011,38:8438-8445.
[17] Ozturk M,Toroslu I H,Fidan G.Heuristic based trading system on Forex data using technical indicator rules [J].Applied Soft Computing,2016,43:170-186.
[18] Kim Y,Ahn W,Oh K J,et al.An intelligent hybrid trading system for discovering trading rules for the futures market using rough sets and genetic algorithms [J].Applied Soft Computing,2017,55:127-140.
[19] 刘宇霞.组合指标个股量化择时交易的实证研究 [J].科技创业月刊,2015,12:19-79.
[20] 丁鹏.量化投资——策略与技术 [M].北京:电子工业出版社,2012.
[21] 梁淇俊,郑贵俊,徐守萍.基于生存分析的择时策略择优体系研究——以技术指标交易信号为例 [J].金融经济学研究,2015,30(1):96-106.
[22] Zhang X Z,Hu Y,Xie K,et al.An evolutionary trend reversion model for stock trading rule discovery [J].Knowledge Based Systems,2015,79:27-35.
[23] Hu Y,Feng B,Zhang X Z,et al.Stock trading rule discovery with an evolutionary trend following model.Expert Systems with Application,2015,42(1):212-222.
[24] 王丝丝,张敬磊,陈慈,张洪宾,马春杰.基于方差与改进群智能算法的K-means聚类优化[J].系统科学与数学,2018,38(10):1117-1127.
[25] 李汉东,张吟,张瑞.基于联合违约概率的资产组合投资优化方法[J].系统工程理论与实践,2018,38(03):556-564.
[26] Arts E,Korst J.Simulated annealing and Boltzmann machines [M].New York:Wiley,1989.
[27] 陈荣达,虞欢欢.基于启发式算法的支持向量机选股模型.系统工程,2014,32(2):40-48.
[28] 黄连忠,万晓跃,孙永刚,王寰宇,王壮.基于模拟退火算法的船舶航速优化研究.船舶,2018,S1:8-17.
[29] Metropolis N,Rosenbluth A W,Rosenbluth M N,Teller A H.Equation of State Calculations by Fast Computing Machines.The Journal of Chemical Physics,1953,21(6):1087-1092.
[30] Kirpatrick S,Gelatt C D,Vecchi M P.Optimization by simulated annealing.Science,1983,220(4598):671-680.
[31] 曹引,冶运涛,梁犁丽,蒋云钟,赵红莉,王浩.高山流域降水无线传感器网络节点布局优化方法[J].系统工程理论与实践,2018,38(8),2168-2176.
[32] 王诺,田玺环,吴迪,吴暖.基于陆海协同的海上战略投送选址——路径优化.系统工程理论与实践,2018,38(11),2929-2941.
[33] Isakov S V,Zintchenko I N,R?nnow T F,Troyer M.Optimised simulated annealing for Ising spin glasses.Computer Physics Communications,2015,192,265-271.
[34] Lyden S,Haque M E.A Simulated Annealing Global Maximum Power Point Tracking Approach for PV Modules Under Partial Shading Conditions.IEEE Transactions on Power Electronics,2016,31(6):4171-4181.
[35] Luo L K,You S Y,Xu Y R,et al.Improving the integration of piece wise linear representation and weighted support vector machine for stock trading signal prediction.Applied Soft Computing,2017,56:199-216.
[36] Duran A,Bommarito M J.A profitable trading and risk management strategy despite transaction costs [J].Quantitative Finance,2011,11(6):829-848.
[37] Lai R K,Fan C,Huang W,et al.Evolving and clustering fuzzy decision tree for financial time series data forecasting [J].Expert Systems with Applications,2009,36:3761-3773.
[38] Hu Y,Liu K,Zhang X,et al.Application of evolutionary computation for rule discovery in stock algorithmic trading:a literature review [J].Applied Soft Computing,2015,36:534-551.