|
|
基于改进TS-DTW距离度量的时间序列聚类
|
Abstract:
基于不同相似性度量的方法对时间序列进行聚类，比较改进TS-DTW距离与其他距离度量相似性在聚类结果上的效果。结果表明基于改进TS-DTW距离度量的聚类结果比其他方法更有效。利用上海证券交易所50指数成分股进行实证研究，采用改进TS-DTW距离进行聚类，聚类结果表明不同类别的股票后续仍具有一定时效性，基于此构建投资组合，得到的时间序列聚类模型有助于降低投资组合的波动风险。
Clustering time series based on different similarity metrics compares the effect of improved TS-DTW distance with other distance metrics of similarity in clustering results. The results show that the clustering results based on the improved TS-DTW distance metric are more effective than other methods. An empirical study is carried out using the constituent stocks of Shanghai Stock Exchange 50 Index, and the clustering results using the improved TS-DTW distance indicate that the follow-up of different categories of stocks is still time-sensitive, based on which the investment portfolios are constructed, and the obtained time-series clustering model helps to reduce the volatility risk of the investment portfolios.
| [1] | Paiva, F.D., Cardoso, R.T.N., Hanaoka, G.P. and Duarte, W.M. (2019) Decision-Making for Financial Trading: A Fusion Approach of Machine Learning and Portfolio Selection. Expert Systems with Applications, 115, 635-655. https://doi.org/10.1016/j.eswa.2018.08.003 |
| [2] | 赵丹丹, 丁建臣. 中国银行业系统性风险预警研究——基于SVM模型的建模分析[J]. 国际商务(对外经济贸易大学学报), 2019(4): 100-113． |
| [3] | Sezer, O.B., Gudelek, M.U. and Ozbayoglu, A.M. (2020) Financial Time Series Forecasting with Deep Learning: A Systematic Literature Review: 2005-2019. Applied Soft Computing, 90, Article 106181. https://doi.org/10.1016/j.asoc.2020.106181 |
| [4] | 张乔夫, 何文明. 基于指数平滑和WKNN的金融时间序列相似性搜索[J]. 现代计算机, 2019(29): 21-25. |
| [5] | 叶建鑫. 基于社交网络用户影响力和时间序列的旅游服务推荐研究与应用[D]: [硕士学位论文]. 重庆: 重庆大学, 2019: 1-56. |
| [6] | 狄瑞彤, 王红, 房有丽. 融合时间序列与多尺度特征的虚假评论识别方法[J]. 计算机工程, 2019, 45(3): 278-285+292. |
| [7] | 许爱东, 李锦涛, 张宇南, 等. 基于动态时间规整的智能电网边缘用电数据去重技术[J]. 南方电网技术, 2020, 14(1): 74-79. |
| [8] | Ailliot, P., Bessac, J., Monbet, V. and Pène, F. (2015) Non-Homogeneous Hidden Markov-Switching Models for Wind Time Series. Journal of Statistical Planning and Inference, 160, 75-88. https://doi.org/10.1016/j.jspi.2014.12.005 |
| [9] | Fu, T. (2011) A Review on Time Series Data Mining. Engineering Applications of Artificial Intelligence, 24, 164-181. https://doi.org/10.1016/j.engappai.2010.09.007 |
| [10] | Berndt, D.J. and Clifffford, J. (1994) Using Dynamic Time Warping to Find Patterns in time Series. KDD Workshop, 10, 359-370. |
| [11] | 陶洋, 邓行, 杨飞跃, 等. 基于DTW距离度量的层次聚类算法[J]. 计算机工程与设计, 2019, 40(1): 116-121. |
| [12] | 夏寒松, 张力生, 桑春艳. 基于LDTW的动态时间规整改进算法[J]. 计算机工程, 2021, 47(11): 108-120. |
| [13] | 李海林, 梁叶, 王少春. 时间序列数据挖掘中的动态时间弯曲研究综述[J]. 控制与决策, 2018, 33(8): 1345-1350. |
| [14] | 邵翔, 郭谋发, 游林旭. 基于改进DTW的接地故障波形互相关度聚类选线方法[J]. 电力自动化设备, 2018, 38(11): 63-70. |
| [15] | Samuelson, P.A. (1967) General Proof That Diversification Pays. The Journal of Financial and Quantitative Analysis, 3, 1-13. https://doi.org/10.2307/2329779 |
