Application of SVM, Decision Tree and Logistic Regression Algorithm in Stock Classification and Prediction

DOI

10.2991/aebmr.k.210917.011How to use a DOI?

Keywords

A-share market, data mining, SVM, decision tree, logistic regression

Abstract

This paper uses three data mining algorithms, support vector machine, decision tree and logical regression, to establish the stock classification prediction model. The paper compares and analyzes the prediction effect of the three models, and summarizes the relationship between the financial indicators of listed companies and their stock intrinsic investment value.The results show that: (1) among the three prediction models, logistic regression model has the best performance, followed by support vector machine model, and decision tree model has the worst performance.(2) The significant influencing factors of stock intrinsic investment value include the actual operation ability, profitability and the continuity and stability of operation. The conclusion of this paper can provide a basis for stock investors to make investment decisions.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Liu Xiaojie
AU  - Liao Aihong
PY  - 2021
DA  - 2021/09/18
TI  - Application of SVM, Decision Tree and Logistic Regression Algorithm in Stock Classification and Prediction
BT  - Proceedings of the 2021 International Conference on Financial Management and Economic Transition (FMET 2021)
PB  - Atlantis Press
SP  - 64
EP  - 68
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.210917.011
DO  - 10.2991/aebmr.k.210917.011
ID  - Xiaojie2021
ER  -