Research Article
Volatile Asset Price Prediction Model Based on Grey Prediction
@INPROCEEDINGS{10.4108/eai.9-12-2022.2327674, author={Zhicheng Fu and Songlin Jia and Zhenxin Guo}, title={Volatile Asset Price Prediction Model Based on Grey Prediction}, proceedings={Proceedings of the 4th Management Science Informatization and Economic Innovation Development Conference, MSIEID 2022, December 9-11, 2022, Chongqing, China}, publisher={EAI}, proceedings_a={MSIEID}, year={2023}, month={3}, keywords={volatile asset grey prediction quasi exponential test residual test}, doi={10.4108/eai.9-12-2022.2327674} }- Zhicheng Fu
Songlin Jia
Zhenxin Guo
Year: 2023
Volatile Asset Price Prediction Model Based on Grey Prediction
MSIEID
EAI
DOI: 10.4108/eai.9-12-2022.2327674
Abstract
How to obtain higher returns in the investment of volatile assets has always been one of the most concerning issues for investors. This is of great significance for the rational planning of financial investment to seek maximum benefits. At present, the mainstream fore-casting methods in related fields include the time series research method, the BP neural network research method, etc. However, these research methods need to take long-term price data as the reference, and cannot accurately describe the gray system of volatile asset price changes. For this reason, the author puts forward a grey prediction model research method that matches the grey system. Firstly, the volatility asset price data of the first seven days were tested to ensure that the data had a quasi-exponential law. Secondly, the above data are used to generate new discrete data columns that weaken randomness. Finally, the differential equation model is established to obtain the approximate estimated value of the original data, to predict the volatility asset price on the eighth-day. This article takes gold and bitcoin as examples to experiment. Based on the data of their historical prices，the price of each seven-day period is used to predict the price of the eighth-day. The residual value is much less than 10%. Therefore, this model can predict the price of volatile assets.