Stock price forecasting for Xiaomi Auto: application of ARIMA and GARCH models

Cao, Yaoyin (2024) Stock price forecasting for Xiaomi Auto: application of ARIMA and GARCH models. In: Vartiak, Lukáš and Cifuentes-Faura, Javier, (eds.) Proceedings of the 8th International Conference on Economic Management and Green Development. Advances in Economics, Management and Political Sciences. EWA Publishing, 56 - 63. ISBN 9781835586990

Text (pdf (2)) - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

Since Xiaomi Corporation entered the market for electric vehicles, the volatility of its stock price has attracted a lot of attention from investors. This study's objective is to foresee the stock price of Xiaomi Auto by constructing GARCH and ARIMA models in R. By conducting a stationarity test and differencing the previous stock price information of Xiaomi Auto, and then the stock price for the upcoming 30 days is predicted using an ARIMA (0,1,0) model. The findings demonstrate that while the ARIMA model predicts a short-term phase of relatively stable stock price, the widening prediction intervals suggest increasing uncertainty. The construction of a GARCH (1,1) model aims to more accurately represent the fluctuations in the stock price. Predictions from the GARCH model point to higher price volatility in coming 30 days. Based on these model outcomes, this paper proposes short-term and medium- to long-term investment strategies for investors and discusses the limitations of the models as well as potential improvement for future research. This research improves the understanding of stock price trends and volatility in the electric vehicle market. It provides practical insights for better investment decisions. The study also advances financial forecasting methods, making them more applicable to real-world market behavior.

Item Type:	Book Section
Additional Information:	© 2024 The Authors
Divisions:	Management
Subjects:	H Social Sciences > HG Finance H Social Sciences > HF Commerce
Date Deposited:	21 Jan 2025 16:15
Last Modified:	21 Jan 2025 16:15
URI:	http://eprints.lse.ac.uk/id/eprint/126990

Actions (login required)

View Item