From statistical arbitrage to big data study
-
摘要: 大数据是一个热门词,但还没有形成严格的理论基础。研究大数据的目的全在于应用。从数学形式来看,大数据与高维高频海量数据区别不大.从统计学的观点来看,研究大数据就是从高维高频的海量数据中找出一个较低维的平稳过程,然后利用大数定律(也叫遍历定理)找到其可用的价值。在金融交易中,这就是统计套利.Abstract: Big data is a hot term. However its strict theoretical basis has not been formed yet.The purpose of research in big data is from its application. From their mathematical formulation,big data and massive high-dimensional and high-frequency data have no big difference. From the statistical point of view, the big data study is to find a lower-dimensional stationary time series from the high-dimensional and high-frequency massive data, then use the law of large numbers(the ergodic theorem) to find the value of its application. In finance, that is just statistical arbitrage.
-
Key words:
- big data /
- stationary time series /
- statistical arbitrage
-
[1] [1] LIU Wei, HUANG Xudong, ZHENG Weian. Black-Scholes’ model and Bollinger bands[J]. Physica A, 2006, 371(2): 565-571.[2] 刘伟. 基于股票市场的随机过程的统计分析[D]. 上海:华东师范大学统计系,2007.[3] 朱威. 股票技术指标的统计分析[D]. 上海:华东师范大学统计系,2006.[4] 李文.股票市场中移动平均技术指标的效果准则和意义探讨[D]. 上海:华东师范大学统计系,2006.[5] 黄旭东. 弱相依系数与技术分析[D]. 上海:华东师范大学统计系,2008.[6] 徐耸. 随机微分方程在金融中的若干应用[D]. 华东师范大学金融与统计学院, 2011.[7] 陈实,吴述金,郑伟安. 中国市场ETF套利研究[J]. 华东师范大学学报:自然科学版, 2013(5): 144-151.[8] 包思,郑伟安,周瑜. 基于MACD的平稳技术指标在高频交易中的应用[J]. 华东师范大学学报:自然科学版, 2013(5): 152-160.[9] 刘畅,郑伟安. 成交价在高频交易中的分析与应用[J]. 华东师范大学学报:自然科学版, 2013(6): 14-21.[10] WANG Zhaodong, ZHENGWeian. High-Frequency Trading and Probability Theory[M]. Singapore: World Scientific, 2014.[11] MAYER-SCHNBERGER V,CUKIER K. Big Data: A Revolution That Will Transform How We Live, Work, and Think[M]. New York: John Murray, 2013.
点击查看大图
计量
- 文章访问数: 2046
- HTML全文浏览量: 72
- PDF下载量: 2922
- 被引次数: 0