Search

In this research, a neural network (NN) model for metal price forecasting based on an evolutionary approach is proposed. Both the neural network model's network parameters and network architecture are selected automatically. The time series metal price data set is used to construct a novel fitness function that takes into account both error minimizations and the reproduction of the auto-correlation function. Calculating the average entropy values allowed the selection of the input parameter count for the neural network model. Gold price forecasting was performed using the proposed methodology. The optimal hidden node number, learning rate, and momentum are 9, 0.026, and 0.76, respectively, according to the evolutionary-based NN model. The proposed strategy is shown to reduce estimation error while also reproducing the auto-correlation function of the time series data set by the validation results with gold price data. The performance of the proposed method is better than other current methods, according to a comparison study. [ABSTRACT FROM AUTHOR]

Fuzzy systems are intensively investigated and extended to construct forecasting models. In particular, intuitionistic fuzzy sets are used to capture higher levels of uncertainty occurring in the modeled data. Neural networks are also used to reflect nonlinearity relationships frequently observed in time series. This paper proposes a new hybrid system merging fuzzy system with neural networks and an advanced optimization technique, the principle of justified granularity. Using this technique, we construct an innovative time-series forecasting model. In the experimental part of the paper, we demonstrate the advantages arising from applying the proposed approach to metal price forecasting. Finally, we provide evidence that the proposed model is competitive with the current state-of-the-art models for the forecasting horizons of one and five days. [ABSTRACT FROM AUTHOR]

This paper tests the hypothesis on the presence of common factors in the dynamics of the Eurasian Economic Union (EAEU) countries’ macroeconomic indicators. As the most important factor, the common dynamics of commodity prices in world markets was chosen. We identified key channels of the transmission of commodity price shocks for EAEU economies. These transmission channels include both direct transmission channels, connected with the terms of trade, and indirect channels. The latter ones include labour migration between EAEU countries, money transactions by migrants, high trade linkages between EAEU countries, and preferential pricing for energy resources. The empirical part of the paper studies the influence of commodity prices on EAEU countries’ macroeconomic indicators. We have proposed a factor autoregressive model. Based on this model, we have identified the first principal component price movements in oil, natural gas, aluminum, copper, steel, gold and wheat. The first principal component explains 75 % of oil and gas price growth rate variation, 45 % of the copper price growth rate variation, and more than 25 % of the variation of other series. Further, we used VAR model to estimate the influence of the first principal component on the EAEU countries’ GDP, consumption and investment dynamics. The results showed the significant positive effect of commodity prices growth in all EAEU members. We also revealed a number of shock transmission features. For example, price shock affected Russian economy through the income effect, while the same shock affected Armenian economy through the direct output stimulation. Our results may be useful for the coordination of the economic policy and business cycles stabilization amongst EAEU countries.

The study is based on hypotheses about the influence of factors on bitcoin value formation. The aim of the article is the scientific inquiry and determination of factors affecting bitcoin value with a high level of correlation. The list of factors includes 33 world indicators, among which there are other cryptocurrencies, fiat money, world indices of stock markets, shares of powerful global companies, prices for energy and precious metals. As a result of the study, independent influential factors are selected and a correlation-regression model of bitcoin value is built. The statistical significance of the factors included in the model and the correlation-regression equation that allows simulating bitcoin value is substantiated. Practical approval of the proposed model using the actual data of the identified influence factors is carried out. Prospects for further research in this direction are based on applying trends as to independent factors that markedly affect the value of a bitcoin in order to model its future value. In addition to the factors identified, a significant influence on bitcoin value can be made by supply and demand, bitcoin scalability, interference of government regulatory institutions, the shadow money market, volume and nature of news in the crypto currency market.

A model for market price modeling in an integrated global model for resource supply has been developed and successfully applied in the WORLD6 model. A dynamic market and price model has been developed, based on immediately tradable amounts, affected by supply and demand. Real-world drivers and a systems approach with feedbacks in the price setting and market mechanisms were used in this study, without the model becoming too complex. Observed cause and effects and feedbacks were included, in order to have explanatory power or be truer to economic reality in terms of both structure and parameter settings. The model is adaptive from a fully free dynamic market to a biased or oligarchic market, depending on the condition. The market price model was parameterized for copper, zinc, lead, nickel, iron, aluminum, wolfram, niobium, molybdenum, lithium, vanadium, gold, silver, platinum, palladium, and tin, and for fossil fuels like oil and hard coal. The equation has the shape: price = k × market amount n, where market amount is the instantly tradable amount of metal in the market arena, k is a metal-specific coefficient, and n is an exponent. The derived equations were applied in the WORLD6 model, making simulations of market price set every day endogenously in the model possible. The price mechanism proposed here perform well in tests against observed data when included in the WORLD6 model. The obtained results were compared to a price curve for coffee and a similar pattern was found. [ABSTRACT FROM AUTHOR]

Mining is the process of extracting a naturally occurring material from the earth to derive a profit. Whether the company make a profit or not depends on many economic parameters, among which the most important are the metal prices on the world market and realized operating costs in the process of exploitation. This work presents the influence of copper price change and value of operating costs on the generated cash flows, i.e. profit, in the case of the open pit South Mining District, which operates within the Copper Mine Majdanpek, Serbia.

There are typically many of variables, which are directly or indirectly associated with the value of underground mine project. Having the ability to plan for uncertainties of input variables is increasingly recognized as critical to longterm mining project success. Large capital intensive projects, such as those in the mineral resource industry, are often associated with diverse sources of both internal and external uncertainties. One of the most external influencing uncertainties is related to the future states of metal price. There are many methods which are applied to forecast the future metal prices, but Mean Reversion Process is one of the most applying methods. This paper analyzes the possibility of using of Grey System Theory to metal price forecasting by examining the correlation between results obtained by these two methods. Intra-class Correlation Coefficient is used as a measure of reliability.

Considering that the development of science and technology depends on metal support, the EU, USA, and China have issued a critical metal list on the development report. However, the scarce and important mineral deposits on a global scale will not be enough to meet the huge needs of economic development in the future. Many fields such as renewable energy, high-performance computing, and AI all require critical metals as essential supports. A proper price regulation of such important metals will contribute to the fair price power on the international market. In this paper, the pricing history and strategy of critical metal support are fully studied and discussed. Since China has become a major consumer country, China should gain fair price power in the market of important metals. [ABSTRACT FROM AUTHOR]

Accurate metal price forecasting is the precondition for optimal and sustainable mine production planning. This paper combined two methods for time series analysis. The developed model represents the combination of the Grey System Theory and a Stochastic differential equation. More precisely, we added stochastic term to the first-order whitenization differential equation. Solution of this equation represents the time response function which is capable of creating artificial evolving paths of the metal price. The simulation process resulted in a distribution and adequate expected value at every single point. Further, model efficiency was increased by adding residuals modeled by the Singular Spectrum Analysis method. The model was tested on the monthly lead metal price series. Mean absolute percentage error is 4.37% and the model can be classified as a high-performance model. [ABSTRACT FROM AUTHOR]