Research on the Stock Price Prediction Model of Banks Based on SVM and BP Neural Network

DOI

10.2991/978-94-6463-198-2_132How to use a DOI?

Keywords

Support Vector Machine; Machine learning; Stock price model prediction; BP neural network

Abstract

The classification and prediction of stock price fluctuation pattern is a very important issue in stock market research in recent years. The rise and fall of stock price directly reflects the change of investors’ assets, and if the rise of stock price can be predicted more accurately, it can provide investors with a certain degree of assisted decision-making.

The banking industry is an important part of the stock market, and the use of models to accurately predict stock price movements is of great practical significance to investors in formulating investment strategies and avoiding market risks, thus more and more scholars are focusing on stock price related research in the banking industry. As stock price movements become more and more complex, simple time series models cannot solve the non-stationarity and non-linearity of stock data, and the shortcomings of traditional linear models are gradually exposed. Historical studies more often use the historical information of individual stocks to predict the future trend of stock prices, and rarely consider the linkage between stocks in the same market. In this paper, we use the information of linked banking stocks for forecasting, and use a combination of neural network and support vector machine to predict stock price patterns. Stock data from January 2020 to June 2020 for the two major indices of the Chinese stock market are used to predict stock trends and stock closing price regressions using two algorithms, support vector machine classification and BP neural network, respectively, and the results show that the prediction results of the support vector machine model after data preprocessing have better prediction results than the original data to build the support vector machine model. This is because they have an average accuracy of 79.13% for support vector machines and 78.7% for BP neural networks. To compare the model accuracy, convolutional neural network and traditional ARIMA model are also built in this paper, and the results show that the support vector machine has the highest prediction accuracy.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Junbin Zhang
AU  - Peiying Zhang
AU  - Jinsui Huang
AU  - Wennan Wang
AU  - Tiancheng Wang
PY  - 2023
DA  - 2023/08/10
TI  - Research on the Stock Price Prediction Model of Banks Based on SVM and BP Neural Network
BT  - Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)
PB  - Atlantis Press
SP  - 1273
EP  - 1280
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-198-2_132
DO  - 10.2991/978-94-6463-198-2_132
ID  - Zhang2023
ER  -