基于多尺度谱映射的基金投资风格显著特征识别方法

›› 2018, Vol. 30 ›› Issue (3): 3-14.

• 经济与金融管理 • 下一篇

基于多尺度谱映射的基金投资风格显著特征识别方法

苏木亚^1,2, 杨晓光², 郭崇慧³

1. 内蒙古大学经济管理学院, 呼和浩特 010021;
2. 中国科学院数学与系统科学研究院, 北京 100190;
3. 大连理工大学管理与经济学部, 大连 116024

收稿日期:2016-12-27 出版日期:2018-03-28 发布日期:2018-03-26
通讯作者: 苏木亚(通讯作者),内蒙古大学经济管理学院副教授,硕士生导师,博士
作者简介:杨晓光,中国科学院数学与系统科学研究院研究员,博士生导师,博士;郭崇慧,大连理工大学管理与经济学部教授,博士生导师,博士
基金资助:
国家自然科学基金项目（61463039；71431008）；中国博士后科学基金项目（2015M581192）；内蒙古自然科学基金项目（2014BS0706）。

A Multi-scale Spectral Mapping Based Method to Identify the Significant Features of Funds' Investment Styles

Sumuya^1,2, Yang Xiaoguang², Guo Chonghui³

1. School of Economics and Management, Inner Mongolia University, Hohhot 010021;
2. Academy of Mathematics and Systems Science, CAS, Beijing 100190;
3. Faculty of Management and Economics, Dalian University of Technology, Dalian 116024

Received:2016-12-27 Online:2018-03-28 Published:2018-03-26

摘要/Abstract

摘要：

风格漂移是证券投资基金常见的现象，辨识投资风格的显著特征对评级和选择证券投资基金有着重要的意义。基于多尺度谱映射的思想，本文提出了一种基金投资风格显著特征识别方法，从逻辑上阐述了该方法的基本原理，用数值模拟展示了该方法相对于传统方法有着明显的优势，并分析了该方法参数选取对识别结果的影响。利用该方法，本文对2012年以来我国24支开放式基金进行了投资风格显著特征的识别，发现这24支基金出现比较严重的风格漂移和趋同现象。

关键词: 多尺度谱映射, 高斯核参数, 投资风格显著特征

Abstract:

Investment style drift is a phenomenon that often occurs in securities investment funds, so identifying the significant features of their investment styles is important for selecting and rating them. Based on spectral mapping idea, we propose a multi-scale spectral mapping based method to identify the significant features of funds' investment styles and then logically expound basic principle of the method. Numerical simulation shows that multi-scale spectral mapping is a much more effective method than traditional ones to identify the significant features of funds' investment styles. In this paper this method is used to identify the significant features of the key investment styles that 24 Chinese open-end funds have taken on since 2012 and the result shows that there exist obvious convergence and drift in their investment styles.

Key words: multi-scale spectral mapping, Gaussian kernel parameter, significant features of investment style

苏木亚, 杨晓光, 郭崇慧. 基于多尺度谱映射的基金投资风格显著特征识别方法[J]. , 2018, 30(3): 3-14.

Sumuya, Yang Xiaoguang, Guo Chonghui. A Multi-scale Spectral Mapping Based Method to Identify the Significant Features of Funds' Investment Styles[J]. , 2018, 30(3): 3-14.

参考文献

[1] Sharpe W. Asset Allocation:Management Style and Performance Measurement[J]. Journal of Portfolio Management, 1992,18(2):7-19
[2] 彭耿. 基金投资风格漂移识别——基于收益和风险双维度[J]. 财经理论与实践, 2014,35(3):37-43
[3] Brookfield D., Su C., Bangassa K. Investment Style Positioning of UK Unit Trusts[J]. European Journal of Finance, 2015,21(10-11):946-970
[4] 孟庆斌,吴卫星,于上尧. 基金经理职业忧虑与其投资风格[J]. 经济研究, 2015,50(3):115-130
[5] 肖继辉,彭文平. 基金经理特征与投资能力、投资风格的关系[J]. 管理评论, 2012,24(7):40-48
[6] 肖继辉. 基金行业锦标赛及其激励效应研究——来自开放式基金的经验证据[J]. 南开管理评论, 2012,15(5):44-55
[7] 肖继辉,彭文平. 锦标赛制度与基金风险调整:理论拓展与经验证据[J]. 管理科学学报, 2015,18(1):87-98
[8] 骆盈盈,任颋. 基金管理模式、投资风格与经营绩效:来自中国公募基金探索性研究[J]. 现代财经, 2015,35(4):22-33
[9] 钱淑芳,许林,吴栩. 宏观经济环境对股票型基金投资风格漂移的影响研究[J]. 投资研究, 2015,9(4):33-45
[10] Wahal S., Yavuz M. Style Investing, Comovement and Return Predictability[J]. Journal of Financial Economics, 2013,107(1):136-154
[11] 易力,胡振华. 风格择时能力对基金绩效的影响研究[J]. 管理评论, 2016,28(4):41-51
[12] 刘莎莎,刘玉珍,唐涯. 信息优势、风险调整与基金业绩[J]. 管理世界, 2013,(8):67-76
[13] 郭文伟. 开放式基金投资风格漂移及风格资产轮换策略研究[D]. 上海交通大学博士学位论文, 2010
[14] Brown S., Goetzmann W. Mutual Fund Style[J]. Journal of Financial Economics, 1997,43(3):373-393
[15] Pattarin F., Paterlini S., Minerva T. Clustering Financial Time Series:An Application to Mutual Funds Style Analysis[J]. Computational Statistics Data Analysis, 2004,47(22):353-372
[16] 杨朝军,蔡明超,徐慧泉. 中国证券投资基金风格分类研究[J]. 上海交通大学学报, 2004,38(3):359-361
[17] 董铁牛,杨乃定,邵予工. 中国开放式基金投资风格分析[J]. 管理评论, 2008,20(7):3-9
[18] Fiedler M. Algebraic Connectivity of Graphs[J]. Czechoslovak Mathematical Journal, 1973,23(2):298-305
[19] Chung F. Spectral Graph Theory[M]. New York:American Mathematical Press, 1997
[20] Luxburg U. A Tutorial on Spectral Clustering[J]. Statistics and Computing, 2007,17(4):395-416
[21] Ng A., Jordan M., Weiss Y. On Spectral Clustering:Analysis and an Algorithm[C]//Advances in Neural Information Processing Systems. Cambridge:MIT Press, 2001
[22] Borjigin S., Guo C. Non-unique Cluster Numbers Determination Methods Based on Stability in Spectral Clustering[J]. Knowledge and Information Systems, 2013,36(2):439-458
[23] Shi J., Malik J. Normalized Cuts and Image Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):888-905
[24] Meila M., Shi J. Learning Segmentation by Random Walks[C]//Advances in Neural Information Processing Systems. Cambridge:MIT Press, 2001

基于多尺度谱映射的基金投资风格显著特征识别方法

A Multi-scale Spectral Mapping Based Method to Identify the Significant Features of Funds' Investment Styles

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价