Stock Volatility Prediction Analysis Based on Different Models

Authors

  • Boao Yang

DOI:

https://doi.org/10.54097/fry0v724

Keywords:

machine learning; stock volatility prediction; ARIMA; XGBOOST; GARCH.

Abstract

Stock volatility prediction is an important method for making the correct financial decision in modern stock market. Additionally, traditional method of stock indices prediction has been proved by modern scholars to be ineffective. This review focuses on the volatility prediction performance of various models, aiming to figure out the most effective volatility prediction model for modern stock market. The four models discussed in this review are ARIMA, XGBOOST, GARCH, and LSTM. Concluding the effectiveness of different models in volatility prediction can be helpful for practical applications of these models in modern stock markets, which can improve the profitability of stock investors under certain situations. Among all four models discussed in this review, LSTM model shows the best performance among all four models in stock volatility prediction. The unique machine learning ability of LSTM has great potential value in future science field research. Since this study is only a general review of stock volatility prediction models, additional research and analysis are essential in order to further conduct this topic for better accuracy and credibility.

Downloads

Download data is not yet available.

References

Ariyo A A, Adewumi A O, Ayo C K. Stock price prediction using the ARIMA model[C]//2014 UKSim-AMSS 16th international conference on computer modelling and simulation. IEEE, 2014, 106-112.

Eslami Ghayour A, Yousefi A. Performance analysis of gradient Boosting Models for forex market prediction. Available at SSRN 4450688.

Forecasting Bitcoin Volatility Using Hybrid GARCH Models with Machine Learning.

Liwei T, Li F, Yu S, et al. Forecast of lstm-xgboost in stock price based on bayesian optimization. Intell. Autom. Soft Comput, 2021, 29(3): 855-868.

Idrees S M, Alam M A, Agarwal P. A prediction approach for stock market volatility based on time series data. IEEE Access, 2019, 7: 17287-17298.

Wang Y, Guo Y. Forecasting method of stock market volatility in time series data based on mixed model of ARIMA and XGBoost. China Communications, 2020, 17(3): 205-221.

Chen T, Guestrin C. Xgboost: A scalable tree boosting system[C]//Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016, 785-794.

Zhu D. Predicting stock volatility based on weighted fusion model of XGBoost and LightGBM[C]//2022 3rd International conference on computer vision, image and deep learning & international conference on computer engineering and applications (CVIDL & ICCEA). IEEE, 2022: 65-67.

Roni B, Wu C, Jewel R K, et al. A study on the volatility of the Bangladesh stock market—based on GARCH type models. Journal of Systems Science and Information, 2017, 5(3): 193-215.

Yu S L, Li Z. Forecasting stock price index volatility with LSTM deep neural network[C]//Recent Developments in Data Science and Business Analytics: Proceedings of the International Conference on Data Science and Business Analytics (ICDSBA-2017). Springer International Publishing, 2018, 265-272.

Downloads

Published

29-12-2023