The Superiority of XGboost Model in the Forecast of Medical Stock Price in the Period of COVID-19

DOI

10.2991/aebmr.k.220405.321How to use a DOI?

Keywords

LSTM; ARIMA; XGBoost; Stock price forecast; COVID-19

Abstract

In this paper, the stock data of Fosun Pharma since the COVID-19 outbreak are used to fit the stock through the traditional statistical analysis model ARIMA, machine learning model XGboost, and deep learning model LSTM, and the future stock prices trend is predicted. It is shown that since the regular term is added to the machine learning model to control the complexity of the model, the generalization ability of the model is improved, and thus making the prediction effect better than the other two models. What’s more, it explains that during the special epidemic period, due to the lack of data and many uncontrollable factors, the quoted data of the deep neural network model are often unrepresentative, resulting in the inconsistent characteristic distribution of the training set and the new data, leading to a series of problems such as over-fitting in the process of predicting individual stocks. Finally, it discusses the differences and advantages of the machine learning model compared with the traditional statistical learning model in the financial field.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Zhaofeng Ma
PY  - 2022
DA  - 2022/04/29
TI  - The Superiority of XGboost Model in the Forecast of Medical Stock Price in the Period of COVID-19
BT  - Proceedings of the 2022 7th International Conference on Social Sciences and Economic Development (ICSSED 2022)
PB  - Atlantis Press
SP  - 1917
EP  - 1925
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.220405.321
DO  - 10.2991/aebmr.k.220405.321
ID  - Ma2022
ER  -