ML-TEA: A set of quantitative investment algorithms based on machine learning and technical analysis

LI Bin, LIN Yan, TANG Wenxuan

Systems Engineering - Theory & Practice ›› 2017, Vol. 37 ›› Issue (5) : 1089-1100.

PDF(1268 KB)
中国科学院数学与系统科学研究院期刊网
PDF(1268 KB)
Systems Engineering - Theory & Practice ›› 2017, Vol. 37 ›› Issue (5) : 1089-1100. DOI: 10.12011/1000-6788(2017)05-1089-12

ML-TEA: A set of quantitative investment algorithms based on machine learning and technical analysis

  • LI Bin1, LIN Yan1, TANG Wenxuan2
Author information +
History +

Abstract

Quantitative investment is an important application of system engineering in the financial investment area. Quantitative investment tries to automatically invest on securities using computational algorithms, and to obtain excess return. This paper proposes a novel quantitative trading algorithm based on machine learning and technical analysis, named "ML-TEA" (machine learning and technical analysis). ML-TEA predicts the stock's movements using the technical indicators calculated by prices and volumes. The empirical results show that firstly, three strategies can obtain an annual return of 25%, which outperforms the index's 10.60% and buy and hold's 3%, and the state of the art algorithms. The three algorithms also significantly outperform the benchmarks and the state of the art in terms of risk adjusted return, i.e., Sharpe ratio, Treynor ratio, and Jensen's alpha. Secondly, Ada-TEA and SVM-TEA can resist reasonable transaction costs that are much higher than the actual transaction costs.

Key words

quantitative investments / machine learning / technical analysis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
LI Bin , LIN Yan , TANG Wenxuan. ML-TEA: A set of quantitative investment algorithms based on machine learning and technical analysis. Systems Engineering - Theory & Practice, 2017, 37(5): 1089-1100 https://doi.org/10.12011/1000-6788(2017)05-1089-12

References

[1] Mitchell T M. Machine learning[M]. New York: McGraw-Hill, 1997.
[2] 杨毓, 蒙肖莲. 用支持向量机(SVM)构建企业破产预测模型[J]. 金融研究, 2006(10): 65-75.
[3] 胡海青, 张琅, 张道宏,等. 基于支持向量机的供应链金融信用风险评估研究[J]. 软科学, 2011, 25(5): 26-30.Hu H Q, Zhang L, Zhang D H, et al. Research on finance credit risk assessment of supply chain based on SVM[J]. Soft Science, 2011, 25(5): 26-30.
[4] 胡海青, 张琅, 张道宏,等. 供应链金融视角下的中小企业信用风险评估研究——基于SVM与BP神经网络的比较研究[J]. 管理评论, 2012, 24(11): 70-80.Hu H Q, Zhang L, Zhang D H, et al. Research on SMEs credit risk assessment from the perspective of supply chain finance-A comparative study on the SVM model and BP model[J]. Management Review, 2012, 24(11): 70-80.
[5] Lo A W, Mamaysky H, Wang J. Foundations of technical analysis: Computational algorithms, statistical inference, and empirical implementation[J]. Journal of Finance, 2000, 55(4): 1705-1770.
[6] Han Y, Yang K, Zhou G. A new anomaly: The cross-sectional profitability of technical analysis[J]. Journal of Financial and Quantitative Analysis, 2013, 48(5): 1433-1461.
[7] Neely C J, Rapach D E, Tu J, et al. Forecasting the equity risk premium: The role of technical indicators[J]. Management Science, 2014, 60(7): 1772-1791.
[8] 韩杨. 对技术分析在中国股市的有效性研究[J]. 经济科学, 2001(3): 49-57.
[9] 沈可挺, 刘煜辉. 中国股市中惯性与反向投资策略的获利模式[J]. 管理科学学报, 2007, 9(6): 43-52.Shen K T, Liu Y H. Investment performance of momentum strategies and contrarian strategies in China stock market[J]. Journal of Management Sciences in China, 2007, 9(6): 43-52.
[10] 韩豫峰, 汪雄剑, 周国富, 等. 中国股票市场是否存在趋势?[J]. 金融研究, 2014(3): 152-163.Han Y F, Wang X J, Zhou G F, et al. Are there trends in Chinese stock markets?[J]. Journal of Financial Research, 2014(3): 152-163.
[11] Gencay R. Non-linear prediction of security returns with moving average rules[J]. Journal of Forecasting, 1996, 15(3): 165-174.
[12] Franses P H, Van Griensven K. Forecasting exchange rates using neural networks for technical trading rules[J]. Studies in Nonlinear Dynamics and Econometrics, 1998, 2(4): 109-114.
[13] Shambora W E, Rossiter R. Are there exploitable inefficiencies in the futures market for oil?[J]. Energy Economics, 2007, 29(1): 18-27.
[14] Kumar L, Pandey A, Srivastava S, et al. A hybrid machine learning system for stock market forecasting[J]. Proceedings of World Academy of Science Engineering and Technology, 2011: 315-318.
[15] Nair B B, Mohandas V P, Sakthivel N R. A decision tree-rough set hybrid system for stock market trend prediction[J]. International Journal of Computer Applications, 2010, 6(9): 1-6.
[16] Kourentzes N, Barrow D K, Crone S F. Neural network ensemble operators for time series forecasting[J]. Expert Systems with Applications, 2014, 41(9): 4235-4244.
[17] Fan A, Palaniswami M. Stock selection using support vector machines[C]//International Joint Conference on Neural Networks, 2001: 1793-1798.
[18] Ince H. Support vector machine for regression and applications to financial forecasting[C]//International Joint Conference on Neural Networks, IEEE Computer Society, 2000: 6348-6348.
[19] Kazem A, Sharifi E, Hussain F K, et al. Support vector regression with chaos-based firefly algorithm for stock market price forecasting[J]. Applied Soft Computing, 2013, 13(2): 947-958.
[20] 禹建丽, 孙增圻, Valeri Kroumov,等. 基于BP神经网络的股市建模与决策[J]. 系统工程理论与实践, 2003, 23(5): 15-19.Yu J L, Sun Z Q, Kroumov V, et al. Stock market forecasting and decision-making based on neural network[J]. Systems Engineering-Theory & Practice, 2003, 23(5): 15-19.
[21] 陈兴, 孟卫东, 严太华. 基于T-S模型的模糊神经网络在股市预测中的应用[J]. 系统工程理论与实践, 2001, 21(2): 66-72.Chen X, Meng W D, Yan T H. Forecasting stock market quotations via fuzzy neural network based on T-S model[J]. Systems Engineering-Theory & Practice, 2001, 21(2): 66-72.
[22] 王文波, 费浦生, 羿旭明. 基于EMD与神经网络的中国股票市场预测[J]. 系统工程理论与实践, 2010, 30(6): 1027-1033.Wang W B, Fei P S, Yi X M. Prediction of China stock market based on EMD and neural network[J]. Systems Engineering-Theory & Practice, 2010, 30(6): 1027-1033.
[23] 于志军, 杨善林, 章政,等. 基于误差校正的灰色神经网络股票收益率预测[J]. 中国管理科学, 2015, 23(12): 20-26.Yu Z J, Yang S L, Zhang Z, et al. Stock returns prediction based on error-correction grey neural network[J]. Chinese Journal of Management Science, 2015, 23(12): 20-26.
[24] 周万隆, 姚艳. 支持向量机在股票价格短期预测中的应用[J]. 商业研究, 2006(6): 160-162.
[25] 陈荣达, 虞欢欢. 基于启发式算法的支持向量机选股模型[J]. 系统工程, 2014, 32(2): 40-48.Chen R D, Yu H H. Stock selection model based on support vector machine within heuristic algorithm[J]. Systems Engineering, 2014, 32(2): 40-48.
[26] 马超, 梁循. 基于支持向量机的上市公司午间公告新闻自动阅读与决策支持系统[J]. 中国管理科学, 2014, 22(S1): 329-335.Ma C, Liang X. An automated midday bulletin news of listed companies read and decision support system based on support vector machine[J]. Chinese Journal of Management Science, 2014, 22(S1): 329-335.
[27] 陈艳, 王宣承. 基于变量选择和遗传网络规划的期货高频交易策略研究[J]. 中国管理科学, 2015, 23(10): 47-56.Chen Y, Wang X C. A study on high-frequency futures trading strategy based on variable selection and genetic network programming[J]. Chinese Journal of Management Science, 2015, 23(10): 47-56.
[28] Yu L, Hu L, Tang L. Stock selection with a novel sigmoid-based mixed discrete-continuous differential evolution algorithm[J]. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(7): 1891-1904.
[29] Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997, 55: 119-139.
[30] Chang C C, Lin C J. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1-27.
[31] Hastie T, Tibshirani R, Friedman J H. The elements of statistical learning[M]. New York: Springer, 2003.
[32] Levin A E. Stock selection via nonlinear multi-factor models[C]//Advances in Neural Information Processing Systems, 1996: 966-972.

Funding

National Natural Science Foundation of China (71401128, 91646206);Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry;Academic Team Building Plan for Young Scholars from Wuhan University (16WSKTD008)
PDF(1268 KB)

1471

Accesses

0

Citation

Detail
Sections
Recommended

/

〈 〉