What do the AI methods tell us about predicting price volatility of key natural resources: Evidence from hyperparameter tuning

Srivastava, Mrinalini; Rao, Amar; Parihar, Jaya Singh; Chavriya, Shubham; Singh, Surendar

doi:10.1016/j.resourpol.2022.103249

Cited by 20 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notwithstanding the increasing popularity of machine learning models and their impressive performance in terms of in‐sample fit and better predictive accuracy compared with other statistical alternatives, their use is fraught with issues of model selection. In particular, their performance depends crucially on the choice of hyperparameters used to tune the neural network (balancing the trade‐off between bias and variance), which can be a nontrivial exercise (Priyadarshini & Cotton, 2021; Srivastava et al, 2023). In the words of Mullainathan and Spiess (2017), “[t]he very appeal of these algorithms is that they can fit many different functions.…”

Section: Literature Review and Research Questionsmentioning

confidence: 99%

Harvesting the volatility smile in a large emerging market: A Dynamic Nelson–Siegel approach

Kumar

Agarwalla

Varma

et al. 2023

Journal of Futures Markets

View full text Add to dashboard Cite

While there is a large literature on modeling volatility smile in options markets, most such studies are eventually focused on the forecasting performance of the model parameters and not on the applicability of the models in a trading environment. Drawing on the analogy of volatility smile like a term structure in the context of interest rates in fixed‐income markets, we evaluate the performance of the Dynamic Nelson–Siegel (DNS) approach to modeling the dynamics of volatility smile in a trading environment against competing alternatives. Using model‐based mispricing as our sorting criterion, and deploying a trading strategy of going long the options in the upper deciles and going short the options in the lower deciles, we show that dynamic models consistently outperform their static counterparts, with the worst dynamic model outperforming the best static model in terms of the percentage of mean returns from the trading portfolios and the Sharpe ratio. Specifically, we find that the DNS model consistently outperforms all other competing specifications on most of our selected criteria.

show abstract

Section: Literature Review and Research Questionsmentioning

confidence: 99%

Harvesting the volatility smile in a large emerging market: A Dynamic Nelson–Siegel approach

Kumar

Agarwalla

Varma

et al. 2023

Journal of Futures Markets

View full text Add to dashboard Cite

show abstract

“…In addition, the implementation of certain patterns may be challenging since they need a significant amount of data and resources connected to computers [8]. It is possible that the models are too reliant on previous data [9,10]. This is due to the inherent volatility of the oil business, which is especially noticeable when it is met with unexpected shocks.…”

Section: Introductionmentioning

confidence: 99%

Managing Economic Uncertainty: Fuzzy Computational Models in International Oil Economy Forecasting

Zhang

2024

Preprint

View full text Add to dashboard Cite

The use of sophisticated computational models for economic forecasting and decision-making is on the rise. Several studies have compared the Hybridization Adaptive Fuzzy Inference System (HAFIS) which is proposed in this research to traditional approaches; this review looks at them all to show how HAFIS is better in several areas, including precision, flexibility, responsiveness, decision support, and long-term planning. The version's accuracy, responsiveness, flexibility, decision support, and strategic making plans talents are more suitable as the included system evolves in phases. The thorough exam of Economic Uncertainty, which is divided into 3 principal impacts: Geopolitical Events, Market Pressures, and Environmental Factors, is the critical process of HAFIS. All of these items integrate to form the unpredictable surroundings that the oil commercial enterprise works in. Economic facts is notoriously misguided, however that is all treated by means of a mixture of rule bases, fuzzy common sense operations. The complicated Forecasting Model, which includes modern Fuzzy Computational Models, is on the middle of this level and can react dynamically to the various troubles posed by means of economic unpredictability and global marketplace tendencies. The fashions use adaptive procedures and fuzzy logic to decipher complex patterns inside the oil enterprise's complex fabric. The endorsed HAFIS method is portrayed as a complete and flexible technique to the challenges of working inside the unpredictable worldwide oil market. The use of actual-world data within the simulation evaluation proved that HAFIS outperformed extra traditional techniques of predicting. Because of its flexibility and flexibility, HAFIS has the potential to generate accurate projections, making it a doubtlessly beneficial asset for everyone involved inside the oil enterprise. In the end, these studies will be of assistance to professionals working in the oil industry in navigating the complexities of the global oil economic system. This will be accomplished via the development of forecasting methodologies and the demonstration of how to realistically apply such models to actual global situations.

show abstract

“…Forecasting gold production is a critical task with significant economic implications for mining companies, investors, and governments [1]. Accurate predictions of gold production enable stakeholders to make informed decisions regarding investment strategies, resource allocation, and market positioning [2].…”

Section: Introductionmentioning

confidence: 99%

Appropriateness of Reduced Modified Three-Parameter Weibull Distribution Function for Predicting Gold Production in Ghana

Obeng,

Nyarko,

Brew

et al. 2023

OJS

View full text Add to dashboard Cite

Forecasting mine production is pertinent to gold mining as it serves as production goals for investors. It is therefore important to identify the exact distribution that gold production as a response variable naturally follows. It is even more appropriate to have a model(s) with few predictor variables. This paper seeks to identify appropriate statistical distribution functions for fitting gold production in Ghana. The empirical paper relied mainly on quarterly secondary datasets on gold production between the years 2009 and 2022 secured from the Minerals Commission of Ghana, Accra. Several known statistical distributions including Weibull, Log-Normal, Generalized Extreme Value (GEV) were explored with Maximum Likelihood Estimation (MLE) and evaluated using model selection criteria as AIC, AICc and BIC. Goodness of Fits were evaluated using Kolmogorov-Smirnov Test (K-S), Cramer-Von Mises Statistic and Anderson-Darling Statistic. Based on the analysis conducted, the reduced modified 3-parameter Weibull distribution provided the best fit for gold production in Ghana. Though the reduced modified Weibull function is proposed, it is important however to recognize that other external factors can influence production levels. Also, the average quarterly fitted gold production is 1000334.8918 ± 75,327.080 (±7.5%) [i.e., 925,007.812 -1,075,661.972]. This indicates that the average annually fitted gold production lies between 3700031.248 and 4302647.888 ounces at 99.9% confidence level. Therefore, the predicted gold production for the year 2022 is 3.7million ounces at 99.9% confidence level.

show abstract

What do the AI methods tell us about predicting price volatility of key natural resources: Evidence from hyperparameter tuning

Cited by 20 publications

References 66 publications

Harvesting the volatility smile in a large emerging market: A Dynamic Nelson–Siegel approach

Harvesting the volatility smile in a large emerging market: A Dynamic Nelson–Siegel approach

Managing Economic Uncertainty: Fuzzy Computational Models in International Oil Economy Forecasting

Appropriateness of Reduced Modified Three-Parameter Weibull Distribution Function for Predicting Gold Production in Ghana

Contact Info

Product

Resources

About