计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 693-698.doi: 10.11896/jsjkx.210300215

• 交叉& 应用 • 上一篇    下一篇

一种多趋势指标结合与择时引入峰值的投资组合优化系统

陈靖邦, 潘俊哲, 沈皓朗, 谷培, 扈明涛   

  1. 暨南大学伯明翰大学联合学院 广州511443
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 扈明涛(humingtao2018051526@stu2018.jnu.edu.cn)
  • 作者简介:cjb2018054910@stu2018.jnu.edu.cn
  • 基金资助:
    国家自然科学基金(61703182,62077028,61877029);中央高校基本科研经费(21617347,21617408,21619404,22wkzd10);广东科技计划项目(2017A040405029,2018KTSCX016,2019A050510024,2019A101002015);广州科技计划项目(201902010041);暨南大学‘国家大学生创新性实验计划'项目(202010559056)

Portfolio Optimization System Based on Multiple Trend Indices with Time Picking of Inducing Peak Prices

CHEN Jing-bang, PAN Jun-zhe, SHEN Hao-lang, GU Pei andHU Ming-tao   

  1. Jinan University-University of Birmingham Joint Institute,Jinan University,Guangzhou 511443,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:CHEN Jing-bang,born in 2000,postgraduate.His main research interests include portfolio optimization and machine learning.
    HU Ming-tao,born in 2000,postgraduate.His main research interests include portfolio optimization and machine learning.
  • Supported by:
    National Natural Science Foundation of China(61703182,62077028,61877029),Fundamental Research Funds for the Central Universities(21617347,21617408,21619404,22wkzd10),Science and Technology Planning Project of Guangdong(2017A040405029,2018KTSCX016,2019A050510024,2019A101002015),Science and Technology Planning Project of Guangzhou,China(201902010041) and Project of ‘National University Student Innovative Experiment Program'of Jinan University(202010559056).

摘要: 趋势表达指标是投资组合优化领域上的一个重要话题。但是大部分基于趋势表达的投资组合优化系统仅仅考虑到了一种指标,而仅考虑到一种指标的系统在不同的数据集上的效果往往差别会比较大,因此文中使用了多趋势指标结合的系统。文中提出的投资组合优化系统使用了一系列径向基函数分别对应3种趋势表达指标(分别是简单移动平均线、指数移动均线、低延迟趋势线),并通过收盘价与短期均线价格之间的关系,对以上3种趋势进行择时,在股票出现上涨趋势的情况下加入最高价格指标(第4个指标)。在这个算法中,一系列的径向基函数会根据近期的投资情况选择最好的趋势表达指标(自适应选择),并根据以最大化下一期财富为目标的凸优化问题的解集进行投资。最后,对本系统和5种常见的投资组合优化系统在两个数据集中进行了横向对比,并取其中较为先进的两种系统在4个数据集上进行了更详细的比较,发现本系统均优于其他系统。

关键词: 低延迟趋势线, 径向基函数, 投资组合优化系统, 指数移动均线, 最高价格指标

Abstract: Trend representation index is an important topic in the field of portfolio optimization.However,most of the portfolio optimization systems based on trend representation only consider one index,and the effect of the system considering only one index is often quite different on different data sets,so we use multiple trend indices in our system.The portfolio optimization system proposed in this paper uses a series of radial basis functions corresponding to three trend representation indices (simple mo-ving average line,exponential moving average line and low-lag trendline) respectively.This system uses the above three indices and adds the peak price index according to the relationship between the closed price and the short-term average price.In this system,the series of radial basis functions will select the best trend expression index (adaptive selection) according to the recent investment situation.Then,the system will make investment according to the solution set of the convex optimization problem which aims at maximizing the wealth of the next period.Finally,the system and five common portfolio optimization systems are compared on two data sets,two of which are chosen to be compared in more detailed on four data sets,and we conclude that our system is better than other systems.

Key words: Exponential moving average line, Low-lag trendline, Peak price index, Portfolio optimization system, Radial basis functions

中图分类号: 

  • O224
[1]MARKOWITZH M.Portfolio selection[J].The Journal of Finance,1952,7(1):77-91.
[2]COVER T M.Universal portfolios[J].Mathematical Finance,1991,1(1):1-29.
[3]SHARPE W F.Capital asset prices:A theory of market equilibrium under conditions of risk[J].The Journal of Finance,1964,19(3):425-442.
[4]SHARPE W F.Mutual fund performance[J].The Journal of Business,1966,39(1):119-138.
[5]FAMA E F.The behavior of stock-market prices[J].The Journal of Business,1965,38(1):34-105.
[6]LI B,HOI S C H.Online portfolio selection:A survey[J].ACM Computing Surveys (CSUR),2014,46(3):35:1-35:36.
[7]HELMBOLD D P,SCHAPIRE R E,SINGER Y,et al.On-line portfolio selection using multiplicative updates[J].Mathematical Finance,1998,8(4):325-347.
[8]GAIVORONSKI A,STELLA F.Stochastic nonstationary optimization for finding universal portfolios[J].Annals of Operations Research,2000,100:165-188.
[9]AGARWAL A,HAZAN E,KALE S,et al.Algorithms for portfolio management based on the newton method[C]//International Conference on Machine Learning.International Machine Learning Society.2006:9-16.
[10]FAMA E F.Efficient capital markets:A review of theory andempirical work[J].The Journal of Finance,1970,25(2):383-417.
[11]JEGADEESH N.Seasonality in stock price mean reversion:Evidence from the U.S.and the U.K[J].The Journal ofFinance,1991,46(4):1427-1444.
[12]BORODIN A,EL-YANIV R,GOGAN V.Can we learn to beat the best stock[J].Journal of Artificial Intelligence Research,2004,21(1):579-594.
[13]LI B,ZHAO P,HOI S,et al.PAMR:Passive aggressive mean reversion strategy for portfolio selection[J].Machine Learning,2012,87(2):221-258.
[14]LI B,HOIS C H,ZHAO P,et al.Confidence weighted mean reversion strategy for online portfolio selection[J].ACM Transactions on Knowledge Discovery from Data,2013,7(1):4.
[15]LI B,HOI S C H,SAHOO D,et al.Moving average reversion strategy for on-line portfolio selection[J].Artificial Intelligence,2015,222:104-123.
[16]HUANG D,ZHOU J,LI B,et al.Robust median reversion stra-tegy for on-line portfolio selection[J].IEEE Transactions on Knowledge and Data Engineering,2016,28(9):2480-2493.
[17]GYÖRFI L,LUGOSI G,UDINA F.Nonparametric kernel-based sequential investment strategies[J].Mathematical Finance,2006,16(2):337-357.
[18]GYÖRFIL,UDINA F,WALK H.Nonparametric nearest neighbor based empirical portfolio selection strategies[J].Statistics and Decisions,2008,26(2):145-157.
[19]LI B,HOI S C H,GOPALKRISHNAN V.Corn:Correlation-driven nonparametric learning approach for portfolio selection[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):article No.21.
[20]WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[21]LAI Z R,DAI D Q,REN C X,et al.Discriminative and compact coding for robust face recognition[J].IEEE Transactions on Cybernetics,2015,45(9):1900-1912.
[22]DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[23]ZHAN Z,CAI J F,GUO D,et al.Fast multiclass dictionarieslearning with geometrical directions in MRI reconstruction[J].IEEE Transactions on Biomedical Engineering,2016,63(9):1850-1861.
[24]LAI Z R,YANG P Y,FANG L D,et al.Short-term sparse portfolio optimization based on alternating direction method of multipliers[J].Journal of Machine Learning Research,2018,19.
[25]LAI Z R,DAI D Q,REN C X,et al.A Peak Price Tracking-Based Learning System for Portfolio Selection[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(7):2823-2832.
[26]LAI Z R,DAI D Q,REN C X,et al.Radial Basis Functions with Adaptive Input and Composite Trend Representation for Portfolio Selection[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(12):6214-6226.
[1] 李春景, 胡静, 唐枝.
基于层次特征的自适应径向基插值图像放大的保真指标
Fidelity Index in Image Magnification Based on Hierarchical Feature and Radial Basis Function
计算机科学, 2019, 46(4): 254-260. https://doi.org/10.11896/j.issn.1002-137X.2019.04.040
[2] 邹鹏, 谌雨章, 陈龙彪, 曾张帆.
基于神经网络的光照分布预测夜视复原算法
Night Vision Restoration Algorithm Based on Neural Network for Illumination Distribution Prediction
计算机科学, 2019, 46(11A): 329-333.
[3] 钱江,王凡,郭庆杰.
二元非张量积型连分式插值
Bivariate Non-tensor-product-typed Continued Fraction Interpolation
计算机科学, 2018, 45(3): 83-91. https://doi.org/10.11896/j.issn.1002-137X.2018.03.014
[4] 甘文道,周城,宋波.
基于RAN-RBF神经网络的网络安全态势预测模型
Network Security Situation Prediction Model Based on RAN-RBF Neural Network
计算机科学, 2016, 43(Z11): 388-392. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.089
[5] 周奚,薛善良.
基于改进的粗糙集和神经网络的WSN故障诊断
WSN Fault Diagnosis with Improved Rough Set and Neural Network
计算机科学, 2016, 43(Z11): 21-25. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.005
[6] 曾祥萍,金炜东,赵海全,李天瑞.
自适应CRBF非线性滤波器及其改进学习算法
Adaptive CRBF Nonlinear Filter and its Improved Learning Algorithm
计算机科学, 2014, 41(7): 266-269. https://doi.org/10.11896/j.issn.1002-137X.2014.07.055
[7] 郝晓丽,张靖.
基于改进自适应聚类算法的RBF神经网络分类器设计与实现
Design and Realization of RBF Neural Network Classifier Based on Advanced Self-adaptive Clustering Algorithm
计算机科学, 2014, 41(6): 260-263. https://doi.org/10.11896/j.issn.1002-137X.2014.06.051
[8] 胡文军,王娟,王培良,王士同.
适合大样本的线性SVMs快速集成模型
Fast Model of Ensembling Linear Support Vector Machines Suitable for Large Datasets
计算机科学, 2014, 41(5): 245-249. https://doi.org/10.11896/j.issn.1002-137X.2014.05.052
[9] 胡蓉,徐蔚鸿.
一种带修剪的增量极速学习模糊神经网络
Pruned Incremental Extreme Leaning Machine Fuzzy Neural Network
计算机科学, 2013, 40(5): 279-282.
[10] 黄宏涛.
一种基于Gaussian函数的双向选择径向基函数神经网络算法

计算机科学, 2007, 34(7): 211-213.
[11] .
基于RBF神经网络的复杂背景下的运动目标检测

计算机科学, 2007, 34(2): 250-252.
[12] 聂烜 赵荣椿 张晓燕 侯云舒 张程.
一种改进的基于径向基函数图像变形方法

计算机科学, 2005, 32(4): 102-103.
[13] 白凌 郭平.
一种提高恒星光谱识别率的新方法

计算机科学, 2004, 31(B07): 59-61.
[14] 钟金宏 杨善林.
FUZZY ARTMAP神经网络综述

计算机科学, 2001, 28(5): 89-92.
[15] 王长琼 孙国正.
一种径向基函数神经网络生成模糊系统的方法研究

计算机科学, 1998, 25(5): 75-76.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!