High-Frequency Forecasting of Stock Volatility Based on Model Fusion and a Feature Reconstruction Neural Network

Shi, Zhiwei; Wu, Zhifeng; Shi, Shuaiwei; Mao, Chengzhi; Wang, Yingqiao; Zhao, Laiqi

doi:10.3390/electronics11234057

Cited by 2 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That notwithstanding, until the 1980's stock market modelling has mainly focused on the mean returns (De Bondt & Thaler, 1985). However, there has been an ever increasing focus and research on forecasting stock market volatility in recent times (Srinivasan & Ibrahim, 2010;Vasudevan & Vetrivel, 2016;Kaya & Güloğlu, 2017;Nguyen & Mai Bui, 2018;Kashyap, 2022;Shi, Wu, Shi, Mao, Wang & Zhao, 2022;Li, Liang & Ma, 2022). This has been achieved by observing the conditional variance which portrays uncertainty of a given time series.…”

Section: Introductionmentioning

confidence: 99%

Modelling and Forecasting volatility in International financial markets

Enow¹

2023

IJRBS

View full text Add to dashboard Cite

Modelling volatility using asset price returns has always been at the forefront of financial economics and option pricing. Observing the conditional variance properties in these asset returns, can be very useful for trend analysis and volatility predictions which are ever needed for trading, portfolio management and financial decision making. The aim of the study was to model and forecast volatility in stock markets. Six financial markets namely the Nasdaq, JSE, the DAX, the CAC 40 and the Nikkei 225 were used as samples with a sampling frame from January 29, 2018 to January 29, 2023. The findings of this study revealed that the variance for all the financial markets under consideration changes significantly with the passage of time. Also, volatility in the JSE, DAX & CAC 40 display fat tail distributions and it is expected to move by three standard deviations. Accordingly, volatility will persist in the Nasdaq, DAX and CAC 40 at an increasing rate but will persist at a decreasing rate in the JSE and Nikkei 225. Considering the peril involved in stock market investing, this study makes a notable contribution to estimating market volatility which is an integral component of asset pricing. With this knowledge, analyst and market traders will have a better understanding of the error distribution in stock markets which will assist in specifying predictive asset prices.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling and Forecasting volatility in International financial markets

Enow¹

2023

IJRBS

View full text Add to dashboard Cite

show abstract

Research on stock price prediction from a data fusion perspective

Li,

Wei,

Shi

et al. 2023

DSFE

View full text Add to dashboard Cite

<abstract> <p>Due to external factors such as political influences, specific events and sentiment information, stock prices exhibit randomness, high volatility and non-linear characteristics, making accurate predictions of future stock prices based solely on historical stock price data difficult. Consequently, data fusion methods have been increasingly applied to stock price prediction to extract comprehensive stock-related information by integrating multi-source heterogeneous stock data and fusing multiple decision results. Although data fusion plays a crucial role in stock price prediction, its application in this field lacks comprehensive and systematic summaries. Therefore, this paper explores the theoretical models used in each level of data fusion (data-level, feature-level and decision-level fusion) to review the development of stock price prediction from a data fusion perspective and provide an overall view. The research indicates that data fusion methods have been widely and effectively used in the field of stock price prediction. Additionally, future directions are proposed. For better performance of data fusion in the field of stock price prediction, future work can broaden the scope of stock-related data types used and explore new algorithms such as natural language processing (NLP) and generative adversarial networks (GAN) for text information processing.</p> </abstract>

show abstract

High-Frequency Forecasting of Stock Volatility Based on Model Fusion and a Feature Reconstruction Neural Network

Cited by 2 publications

References 46 publications

Modelling and Forecasting volatility in International financial markets

Modelling and Forecasting volatility in International financial markets

Research on stock price prediction from a data fusion perspective

Contact Info

Product

Resources

About