Financial hedging in energy market by cross-learning machines

Chen, An-Sing; Leung, Mark T.; Pan, Shaotao; Chou, Ching-Yun

doi:10.1007/s00521-019-04572-4

Cited by 6 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Financial market participants are mainly e-commerce sellers and e-commerce buyers, traders (risk), and arbitrageurs (buying multiple options at once to lock in risk opportunities) [19][20][21]. First, market participants send trade orders to the option pricing model system and instruct managing brokers in financial transactions to trade for them.…”

Section: Option Transaction Processmentioning

confidence: 99%

Correlation Financial Option Pricing Model and Computer Simulation under a Stochastic Interest Rate

Yin¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the continuous expansion of the consumer interest rate market today, the risks brought by interest rate fluctuations have had a huge and far-reaching impact on the financial markets of many countries and it is becoming more and more important to simulate the pricing of financial options. In the traditional pricing model of financial options, the pricing standard of the pricing model is generally set as a financial product with random disturbance characteristics and the market price of its transaction does not follow the arbitrage principle of financial product pricing. It is easy to generate errors and cause risks, and the accuracy of traditional financial option pricing models is not high, and the simulation time is long, which greatly reduces the rate of financial transactions. To improve the accuracy of option pricing models, this paper uses computer simulation technology to simulate the pricing of correlated financial options under stochastic interest rates. From the four aspects of error, risk parameters, success rate, and simulation time, it is tested to observe the influence of computer simulation technology on the financial option pricing model. The final results show that by using computer simulation technology, the error of the correlation financial option pricing model under the random interest rate is reduced, the success rate is improved, the risk parameter is reduced by 3.03%, and the simulation time is reduced by 0.605 seconds.

show abstract

Section: Option Transaction Processmentioning

confidence: 99%

Correlation Financial Option Pricing Model and Computer Simulation under a Stochastic Interest Rate

Yin¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Kou et al [51] provides a comprehensive list of methods for and objectives for developing systematic risk analysis based on big data solution. Although there are large number of researches proposing the machine learning methods (as it is suitable for big data analytics) for hedging energy price risks (see, [52,53] for example), there are not many studies focusing on developing big data solutions, specifically for the energy price risk. The main challenge in developing such solutions, is to access the multiple data warehouses and fussing the results from different sources [53].…”

Section: Practical Issues and Challengesmentioning

confidence: 99%

Big Data and Energy Security: Impacts on Private Companies, National Economies and Societies

Hassani

Komendantova

Kroos³

et al. 2021

Preprint

View full text Add to dashboard Cite

The importance of energy security for successful functioning of private companies, national economies, and the overall society should not be underestimated. Energy is a critical infrastructure for any modern society, and its reliable functioning is essential for all economic sectors and for the well-being of everybody. Uncertainty in terms of the availability of information, reliable data to make predictions and to plan for investment as well as for other actions of stakeholders at the energy markets is one of the factors, which has the highest influence on energy security. This uncertainty can be connected with many factors such as the availability of reliable data or the actions of stakeholders themselves. For example, the recent outbreak of the COVID-19 pandemic revealed negative impacts of uncertainty on decision-making processes and markets. At the time point when the market participants started to receive real-time information about the situation, the energy markets began to ease. This is one scenario where Big Data can be used to amplify information to various stakeholders to prevent panic and to ensure market stability and security of supply. In a fast-paced digital world characterized by technological advances, the use of Big Data technology provides a unique niche point to close this gap in information disparity by levering the use of unconventional data sources to integrate technologies, stakeholders, and markets to promote energy security and market stability. The potential of Big Data technology is yet to be fully utilized. Big Data can handle large data set characterized by volume, variety, velocity, value, and complexity. The challenge for energy markets is to leverage this technology to mine available socioeconomic, political, geographic, and environmental data responsibly as well as to provide indicators that predict future global supply and demand. This information is crucial for energy security and ensuring global economic prosperity.

show abstract

The correlation between green finance and carbon emissions based on improved neural network

Sun

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Financial hedging in energy market by cross-learning machines

Cited by 6 publications

References 44 publications

Correlation Financial Option Pricing Model and Computer Simulation under a Stochastic Interest Rate

Correlation Financial Option Pricing Model and Computer Simulation under a Stochastic Interest Rate

Big Data and Energy Security: Impacts on Private Companies, National Economies and Societies

The correlation between green finance and carbon emissions based on improved neural network

Contact Info

Product

Resources

About