Comparative Empirical Study on CAPM and Stock Price Prediction by BP Neural Network in Shanghai’s A-share

DOI

10.2991/assehr.k.200401.049How to use a DOI?

Keywords

CAPM, stock price prediction, BP neural network

Abstract

Capital Asset Pricing Model (CAPM) is aimed to quantify the relationship between risk and expected rate of return. It has been tested and improved constantly by a number of researchers both abroad and in China. This study achieves a comparative empirical test of CAPM on E-V model, E-S model and GLS model in Shanghai A-share market. However, all of three model cannot adapt to Shanghai A-share market wonderfully. Now, computer science is a new instrument that can be applied to describe the capital market. Therefore, as a comparison of results, we select a single stock and use the simplest neural network, BP neural network with algorithms to optimize the weights and thresholds between the network layers for prediction. The results show that machine learning is a good method for stock prediction compared with only considering a single factor, which should be further explored in our future learning.

Copyright

© 2020, 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  - Man Fang
AU  - Xuefei Wang
AU  - Mengting Zhang
AU  - Yue Li
AU  - Jingyi Zhang
PY  - 2020
DA  - 2020/04/06
TI  - Comparative Empirical Study on CAPM and Stock Price Prediction by BP Neural Network in Shanghai’s A-share
BT  - Proceedings of the International Conference on Education, Economics and Information Management (ICEEIM 2019)
PB  - Atlantis Press
SP  - 225
EP  - 232
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.200401.049
DO  - 10.2991/assehr.k.200401.049
ID  - Fang2020
ER  -