China
Africa
Explore chapters and articles related to this topic
Predicting Stock Return Risk and Volatility Using Neural Network
Published in Noura Metawa, M. Kabir Hassan, Saad Metawa, Artificial Intelligence and Big Data for Financial Risk Management, 2023
Maha Metawea, Saad Metawa, Noura Metawa
There are several definitions of stock return volatility. According to one of the leading definitions in this area, volatility is defined as a statistical measurement of the changes in returns or market index (Almasi Monfared and Enke, 2014) Volatility can be measured using either the standard deviation or variance between returns from the market index. Typically, a higher degree of volatility is considered more dangerous for stability in the field of finance. Other scholars in the area define volatility as the degree of variation in a series of trading returns over a certain period of time (Chaudhuri and Ghosh 2016). Volatility is commonly measured by the standard deviation of returns where the symbol “σ” is used as a measure of volatility, which should not be confused with the variance of the same name, which instead σ2 (Table 5.1).
Relations between trade volume and frequency of domestic investors with stock volatility: Analysis before and during the COVID-19 pandemic
Published in Siska Noviaristanti, Contemporary Research on Management and Business, 2023
Indonesia Central Depository (ICSD) divides investors into Individuals and Institutions comprising Securities Companies, Mutual Funds, Pension Funds, Corporations, Banks, Insurance, Foundations, and Others. In this study, the nine types of investors are grouped into Individual Investors (ID), Financial Institution Investors (FIN), and Non-Financial Institution Investors (Non-FIN). Bian et al. (2020) investigated the participation role of investors in the relationship between volatility and volume. The study found that volatility has a positive relationship with retail traders and institutional investors. This study proved that an increase in the investors trading on a stock increases the stock’s volatility.
Analysis of Dynamic Data
Published in Shyama Prasad Mukherjee, A Guide to Research Methodology, 2019
Volatility has been simply defined as a measure of variability like the standard deviation or the coefficient of variation of change (during successive periods). In the case of a stationary time series when the expectation of change is taken as zero, standard deviation is the measure of volatility. Thus, if Pt t = 1, 2, … T denotes the series on price and changes are measured by log Pt / Pt−1 = Rt (something like the rate of return) then the SD σ of Rt defines volatility, usually with annual data, and then we can consider √ 12 σ as the monthly measure and √ 52 σ as the weekly measure, if we so need. Estimation of σ from sample data can be carried out in several possible ways, depending on the data we use and the average we choose. Thus we can use all the available data or only a recent part after some possible innovation. The average could be a historical average or a moving average or an exponentially weighted moving average. In fact, the overall variance versus the conditional variance is a big issue even in defining and interpreting volatility.
Realised volatility prediction of high-frequency data with jumps based on machine learning
Published in Connection Science, 2023
Gao Yuyan, He di, Mu Yan, Zhao Hongmin
Volatility is an important indicator for measuring financial risk, and the accuracy of predictions directly affects investors' budget decisions. Therefore, the accuracy of volatility has always been a concern. Based on high-frequency individual stock data, this paper constructs HARQ-J and HARQ-F-J models by introducing jump variables into HARQ and HARQ-F models, combines traditional models with machine learning to perform out-of-sample prediction, and compares and analyses the results with traditional models. The following conclusions are drawn: (1) The prediction accuracy of HARQ-J and HARQ-F-J models is significantly better than the original model, However, not all stock data are used to reduce volatility prediction errors by adding jump variables to the model. Therefore, a specific analysis is required based on the characteristics of individual stocks. (2) The traditional method and hybrid model can find that the latter has significantly better volatility prediction results after adjusting parameters compared to the traditional model, and its performance is more stable. (3) From the MCS test results, we can find that HARQ-F-J-LSTM model has the highest prediction accuracy among the six models, with HARQ-F-LSTM model taking the second place six models, with HARQ-F-LSTM model taking the second place.
Developing an early warning system for the shipping industry in Korea using two approaches
Published in Maritime Policy & Management, 2022
Sunghwa Park, Janghan Kwon, Taeil Kim
In the finance sector, the LIBOR interest rates, the VIX, the Dow Jones Industrial Average, and the Korean shipping stock index are included. The LIBOR interest rate is used to reflect the capital-intensive nature of the shipping industry as interest rates could affect cash-flow and liquidity problems for individual companies (Alexandridis et al. 2018). The VIX represents the volatility of the listed S&P 500 Index Options and is forward projected for 30 days. The VIX is used as a proxy variable for macroeconomic uncertainty in many studies (Bloom 2009; Baker, Bloom, and Davis 2016). During periods in which economic uncertainty increases, economic agents postpone decisions and tend to wait until the uncertainty is resolved (Bloom 2009). This ‘wait-and-see’ behavior can be found in the shipping market by observing the impact of an uncertainty shock. In a situation of heightened uncertainty, shipowners tend to postpone their newbuilding orders, since increased uncertainty can delay investment, especially when the capital stock is more irreversible (Fuss and Vermeulen 2008). Further, an uncertainty shock may reduce GDP growth, which is related to the demand of the shipping market.
Pricing real options based on linear loss functions and conditional value at risk
Published in The Engineering Economist, 2020
Volatility is one of the important variables in valuation of options. Unlike a stock, real assets are not likely to have any historical data available to estimate the annualized changes in project value. Han and Park (2008) proposed a method by using an analytical relationship between the project volatility (σ) and the parameters of project value distribution at the option life. In any project analysis, we need to estimate the anticipated cash flows associated with undertaking an investment. To determine the project value at the option life, we may attempt to estimate what the future cash flow series look like beyond the option life. Since these project cash flows are random variables described by probability distributions, we may find the project value distribution by aggregating these random cash flow distributions. If we know the exact probability distributions, we may obtain the project value distribution by either an analytical method or using the Monte Carlo simulation method.