J Shanghai Jiaotong Univ Sci

Journal of Shanghai Jiaotong University(Science) >

2017 , Vol. 22 >Issue 2: 193 - 197

DOI: https://doi.org/10.1007/s12204-017-1821-9

Big Data Framework for Quantitative Trading System

Expand
  • (1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China; 2. Shanghai Key Laboratory of Financial Information Technology, Shanghai University of Finance and Economics, Shanghai 200433, China)

Online published: 2017-04-04

Fold

Abstract

Massive trading data are produced in securities market every day. Besides, the amount of relevant social media data is also growing fast. It is a vital problem of making use of these data. Facing on the growing amount of data, using big data framework is a necessary and reasonable method. Then, a big data framework for quantitative trading system is proposed in this paper. In the framework, Apache Spark is chosen as the distributed computing framework to process trading data, and Apache HBase as the distributed database is used to store data. After introducing the whole framework, we discussed data sources and the structure of quantitative trading layer in detail.

Key words： big data; framework; quantitative trading; Apache Spark

Cite this article

DAI Shuji1 (戴书吉), WU Xing1,2* (武星), PEI Mengqi1 (裴孟齐), DU Zhikang1 (杜智康) . Big Data Framework for Quantitative Trading System[J]. Journal of Shanghai Jiaotong University(Science), 2017 , 22(2) : 193 -197 . DOI: 10.1007/s12204-017-1821-9

References

[1] KAUFFMAN R J, HU Y, MA D. Will high-frequencytrading practices transform the financial markets in theAsia Pacific Region? [J]. Financial Innovation, 2015,1(1): 1-27. [2] KEARNS M, ORTIZ L. The Penn-Lehman automatedtrading project [J]. IEEE Intelligent Systems, 2003,18(6): 22-31. [3] TRELEAVEN P, GALAS M, LALCHAND V. Algorithmictrading review [J]. Communications of theACM, 2013, 56(11): 76-85. [4] ZAHARIA M, CHOWDHURY M, FRANKLIN MJ, et al. Spark: Cluster computing with workingsets [C]//Proceedings of the 2nd USENIX Conferenceon Hot Topics in Cloud Computing. Boston, MA:USENIX Association, 2010: 1765-1773. [5] SPARK A. Spark programming guide [EB/OL].(2015-10-4). [2016-11-14]. http://spark.apache.org/docs/latest/programming-guide.html. [6] SPARK A. Apache spark–lightning-fast cluster computing[EB/OL]. (2014-4-21). [2016-11-14]. http://spark.apache.org/. [7] VORA M N. Hadoop-HBase for large-scale data[C]//Computer Science and Network Technology(ICCSNT), 2011 International Conference. Harbin:IEEE, 2011: 601-605. [8] NARANG R K. Inside the black box: the simple truthabout quantitative trading [M]. Canada: John Wiley& Sons, 2009. [9] GRUNDY B D, KIM Y. Stock market volatility ina heterogeneous information economy [J]. Journal ofFinancial and Quantitative Analysis, 2002, 37(1): 1-27. [10] KWON K Y, KISH R J. A comparative study of technicaltrading strategies and return predictability: Anextension of Brock, Lakonishok, and LeBaron (1992)using NYSE and NASDAQ indices [J]. The QuarterlyReview of Economics and Finance, 2002, 42(3): 611-631.
Options
Outlines

/

〈 〉