Research of stock trends based on data mining

ShaoChen Yang; RuiQi Wang

doi:10.1109/ICBDIE52740.2021.00029

Research of stock trends based on data mining

ShaoChen Yang
, RuiQi Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Stock price fluctuations are highly uncertain, and there are many random factors that affect fluctuations. Therefore, we try to use basic data of stock to calculate indicators to measure stock trends and use machine learning methods to build stock trend prediction models. This study selects and calculates ten trending technical indicators based on the individual stock data of China's Shanghai Stock Exchange A shares in the past three years, using support vector machines (SVM), twin support vector machines (TWSVM) and local weighted twin support vector machine (WLTSVM) to build a trend prediction model. This article compares the effects of the above three theoretical models on stock trend prediction. Experiments show that the model based on WLTSVM has better performance than the traditional SVM model and TWSVM model.

© 2021 IEEE

Original language	English
Title of host publication	Proceedings - 2021 2nd International Conference on Big Data and Informatization Education (ICBDIE 2021)
Publisher	IEEE
Pages	92-96
ISBN (Electronic)	978-1-6654-3870-4
DOIs	https://doi.org/10.1109/ICBDIE52740.2021.00029
Publication status	Published - 2021
Externally published	Yes
Event	2021 2^nd International Conference on Big Data and Informatization Education (ICBDIE2021) - Hangzhou, China Duration: 2 Apr 2021 → 4 Apr 2021 http://2021.icbdie.org/

Conference

Conference	2021 2^nd International Conference on Big Data and Informatization Education (ICBDIE2021)
Abbreviated title	ICBDIE2021
Place	China
City	Hangzhou
Period	2/04/21 → 4/04/21
Internet address	http://2021.icbdie.org/

Research Keywords

weighted twin support vector machine with local information (WLTSVM)
twin support vector machine (TWSVM)
support vector machine (SVM)
trend prediction

Access Output

10.1109/ICBDIE52740.2021.00029

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{1b9c17b478e447b99d68c6aed687aaf9,

title = "Research of stock trends based on data mining",

abstract = "Stock price fluctuations are highly uncertain, and there are many random factors that affect fluctuations. Therefore, we try to use basic data of stock to calculate indicators to measure stock trends and use machine learning methods to build stock trend prediction models. This study selects and calculates ten trending technical indicators based on the individual stock data of China's Shanghai Stock Exchange A shares in the past three years, using support vector machines (SVM), twin support vector machines (TWSVM) and local weighted twin support vector machine (WLTSVM) to build a trend prediction model. This article compares the effects of the above three theoretical models on stock trend prediction. Experiments show that the model based on WLTSVM has better performance than the traditional SVM model and TWSVM model. {\textcopyright} 2021 IEEE",

keywords = "weighted twin support vector machine with local information (WLTSVM), twin support vector machine (TWSVM), support vector machine (SVM), trend prediction",

author = "ShaoChen Yang and RuiQi Wang",

year = "2021",

doi = "10.1109/ICBDIE52740.2021.00029",

language = "English",

pages = "92--96",

booktitle = "Proceedings - 2021 2nd International Conference on Big Data and Informatization Education (ICBDIE 2021)",

publisher = "IEEE",

address = "United States",

note = "2021 2<sup>nd</sup> International Conference on Big Data and Informatization Education (ICBDIE2021), ICBDIE2021 ; Conference date: 02-04-2021 Through 04-04-2021",

url = "http://2021.icbdie.org/",

}

TY - GEN

T1 - Research of stock trends based on data mining

AU - Yang, ShaoChen

AU - Wang, RuiQi

PY - 2021

Y1 - 2021

N2 - Stock price fluctuations are highly uncertain, and there are many random factors that affect fluctuations. Therefore, we try to use basic data of stock to calculate indicators to measure stock trends and use machine learning methods to build stock trend prediction models. This study selects and calculates ten trending technical indicators based on the individual stock data of China's Shanghai Stock Exchange A shares in the past three years, using support vector machines (SVM), twin support vector machines (TWSVM) and local weighted twin support vector machine (WLTSVM) to build a trend prediction model. This article compares the effects of the above three theoretical models on stock trend prediction. Experiments show that the model based on WLTSVM has better performance than the traditional SVM model and TWSVM model. © 2021 IEEE

AB - Stock price fluctuations are highly uncertain, and there are many random factors that affect fluctuations. Therefore, we try to use basic data of stock to calculate indicators to measure stock trends and use machine learning methods to build stock trend prediction models. This study selects and calculates ten trending technical indicators based on the individual stock data of China's Shanghai Stock Exchange A shares in the past three years, using support vector machines (SVM), twin support vector machines (TWSVM) and local weighted twin support vector machine (WLTSVM) to build a trend prediction model. This article compares the effects of the above three theoretical models on stock trend prediction. Experiments show that the model based on WLTSVM has better performance than the traditional SVM model and TWSVM model. © 2021 IEEE

KW - weighted twin support vector machine with local information (WLTSVM)

KW - twin support vector machine (TWSVM)

KW - support vector machine (SVM)

KW - trend prediction

UR - https://www.scopus.com/pages/publications/85113416897

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85113416897&origin=recordpage

U2 - 10.1109/ICBDIE52740.2021.00029

DO - 10.1109/ICBDIE52740.2021.00029

M3 - RGC 32 - Refereed conference paper (with host publication)

SP - 92

EP - 96

BT - Proceedings - 2021 2nd International Conference on Big Data and Informatization Education (ICBDIE 2021)

PB - IEEE

T2 - 2021 2<sup>nd</sup> International Conference on Big Data and Informatization Education (ICBDIE2021)

Y2 - 2 April 2021 through 4 April 2021

ER -

Research of stock trends based on data mining

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this