A Study of Early Warning System in Volume Burst Risk Assessment of Stock with Big Data Platform

被引：2
作者：
Shih, Dong-Her [1 ]
Hsu, Hsiang-Li [1 ]
Shih, Po-Yuan [2 ]
机构：
[1] Natl Yunlin Univ Sci & Technol, Dept Informat Management, Touliu, Yunlin, Taiwan
[2] Natl Yunlin Univ Sci & Technol, Dept Finance, Touliu, Yunlin, Taiwan
来源：
2019 IEEE 4TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYSIS (ICCCBDA) | 2019年
关键词：
spark; big data; stock trading volume analysis; risk assessment; DECISION TREE; MODEL; PREDICTION; INVESTMENT; DISCOVERY; SELECTION;
D O I：
10.1109/icccbda.2019.8725738
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The high remuneration of stock market has attracted most investors. However, there are many factors affecting the trading price fluctuations in the stock market. In order to reduce the investment risk investor may use many measuring tools. The prediction of stock trading price is one of the most important topics in financial market. Financial time series forecasting is a popular application of machine learning methods. Previous research reports that advanced forecasting methods can accurately predict the trading price changes in financial markets. This study intends to use the real-time stream data processing architecture in the big data Spark framework to analyze the real-time stock trading volume according to the bursting comprehensive index of trading volume, and send risk notifications according to different trading volume levels. Investors can choose the best timing to invest. The results of this study show that investors who want to operate in high-risk environment can use stock trading volume risk rating criteria to increase profit.
引用
收藏
页码：244 / 248
页数：5
相关论文
共 29 条
[1]   A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction [J].
Chen, Yingjun ;
Hao, Yongtao .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 80 :340-355
[2]   Financial time series pattern matching with extended UCR Suite and Support Vector Machine [J].
Gong, Xueyuan ;
Si, Yain-Whar ;
Fong, Simon ;
Biuk-Aghai, Robert P. .
EXPERT SYSTEMS WITH APPLICATIONS, 2016, 55 :284-296
[3]   Rock burst assessment and prediction by dynamic and static stress analysis based on micro-seismic monitoring [J].
He, Jiang ;
Dou, Linming ;
Gong, Siyuan ;
Li, Jing ;
Ma, Zhiqiang .
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES, 2017, 93 :46-53
[4]   Booms, busts and behavioural heterogeneity in stock prices [J].
Hommes, Cars ;
in 't Veld, Daan .
JOURNAL OF ECONOMIC DYNAMICS & CONTROL, 2017, 80 :101-124
[5]   Stock trading rule discovery with an evolutionary trend following model [J].
Hu, Yong ;
Feng, Bin ;
Zhang, Xiangzhou ;
Ngai, E. W. T. ;
Liu, Mei .
EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (01) :212-222
[6]   A modern neural network model to do stock market timing on the basis of the ancient investment technique of Japanese Candlestick [J].
Jasemi, Milad ;
Kimiagari, Ali M. ;
Memariani, A. .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (04) :3884-3890
[7]   Damage constitutive equations and its application to fiber reinforced composites under transverse impact [J].
Jiang, DZ ;
Shen, W ;
Wang, XY .
APPLIED COMPOSITE MATERIALS, 2002, 9 (05) :315-329
[8]   Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index [J].
Kim, KJ ;
Han, I .
EXPERT SYSTEMS WITH APPLICATIONS, 2000, 19 (02) :125-132
[9]   Expert system for predicting stock market timing using a candlestick chart [J].
Lee, KH ;
Jo, GS .
EXPERT SYSTEMS WITH APPLICATIONS, 1999, 16 (04) :357-364
[10]   Financial distress prediction based on OR-CBR in the principle of k-nearest neighbors [J].
Li, Hui ;
Sun, Jie ;
Sun, Bo-Liang .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (01) :643-659
123