Research on Investment Decisions of Open-ended Funds Based on Decision Tree, RF and LGBM during COVID-19

DOI

10.2991/aebmr.k.220405.024How to use a DOI?

Keywords

open-ended funds; COVID-19; random forest; LGBM; investment advice

Abstract

Since the onset of COVID-19, global economic development has not been as good as it used to be, so more and more people are looking to earn more money by investing besides working. The open-ended fund has a broad market. In addition, open-ended funds have many options. It is appropriate for all types of people with varying levels of risk tolerance and investment ability. During the pandemic, the risk resistance of investment products is always one of the most important factors for people to consider whether to invest. Therefore, this paper aims to screen open-ended funds with good risk resistance during the epidemic through machine learning. In this paper, the anti-risk ability of funds is determined according to the annual return rate of each fund since the epidemic. Ten indicators such as Sharpe ratio and Treynor performance measure are used to measure the anti-risk ability of funds during the epidemic from two dimensions including funds and fund managers. Then decision tree, random forest, random forest optimization model, LGBM model are established. It uses these models to predict the fund’s anti-risk ability. Finally, the author finds the best model according to the accuracy. The LGBM model has the highest prediction accuracy, 93.5% of the fund’s risk resistance ability types, and the model’s prediction accuracy rate of excellent funds is 71.43%.

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  - Ruihua Zhou
PY  - 2022
DA  - 2022/04/29
TI  - Research on Investment Decisions of Open-ended Funds Based on Decision Tree, RF and LGBM during COVID-19
BT  - Proceedings of the 2022 7th International Conference on Social Sciences and Economic Development (ICSSED 2022)
PB  - Atlantis Press
SP  - 137
EP  - 141
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.220405.024
DO  - 10.2991/aebmr.k.220405.024
ID  - Zhou2022
ER  -