Research Article
Portfolio Allocation Using Monte Carlo Simulation and ARIMA Model Targeting Chinese Companies Trading on the US Stock Exchange
@INPROCEEDINGS{10.4108/eai.18-11-2022.2326875, author={Yuxuan Chen and Tingsong Li and Leyao Lin}, title={Portfolio Allocation Using Monte Carlo Simulation and ARIMA Model Targeting Chinese Companies Trading on the US Stock Exchange}, proceedings={Proceedings of the 4th International Conference on Economic Management and Model Engineering, ICEMME 2022, November 18-20, 2022, Nanjing, China}, publisher={EAI}, proceedings_a={ICEMME}, year={2023}, month={2}, keywords={component; portfolio allocation; chinese corporation analysis; us stock market; monte carlo simulation; arima model}, doi={10.4108/eai.18-11-2022.2326875} }- Yuxuan Chen
Tingsong Li
Leyao Lin
Year: 2023
Portfolio Allocation Using Monte Carlo Simulation and ARIMA Model Targeting Chinese Companies Trading on the US Stock Exchange
ICEMME
EAI
DOI: 10.4108/eai.18-11-2022.2326875
Abstract
Against the background of the COVID-19 pandemic, stock markets around the world have been greatly impacted. The Chinese stocks face the risk render by pandemics and face the crackdown from the Chinese government. This study aims to evaluate the portfolio allocation with the U.S.-listed Chinese stocks. In this paper, first, we calculate the Sharpe ratio of all Chinese companies that trade on U.S. major stock markets and choose six stocks with the largest Sharpe ratio to do asset allocation. The stocks that we choose are SPI, AACG, BTB, MOXC, DQ and RENN. Then we plot the efficient frontier by the Monte Carlo simulation method to find the maximum Sharpe Ratio portfolio and minimum volatility portfolio, and view the performance of each portfolio. We get a similar composition of stocks in these two portfolios, which have a high Sharpe ratio and high volatility. In conclusion, we can say that allocations with pure Chinese stocks may not be suitable for risk-averse people. Finally, we use the ARIMA model to predict the future 21 days returns of each stock. We calculate the AIC to evaluate the model and plot the prediction of stocks’ returns and compare it with the real value which the stocks show. As a result, we find that the ARIMA model only has limited accuracy in predicting the future.